API tools faq
paste
Advertisement
Guest User

xformers

a guest
Dec 13th, 2022
773
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 364.58 KB | None | 0 0
raw download clone embed print report
  1. Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
  2. Obtaining file:///F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers
  3. Preparing metadata (setup.py) ... done
  4. Requirement already satisfied: torch>=1.12 in f:\python 3.10.8\lib\site-packages (from xformers==0.0.15.dev0+ed99125.d20221213) (1.13.0+cu117)
  5. Requirement already satisfied: numpy in f:\python 3.10.8\lib\site-packages (from xformers==0.0.15.dev0+ed99125.d20221213) (1.23.5)
  6. Requirement already satisfied: pyre-extensions==0.0.23 in f:\python 3.10.8\lib\site-packages (from xformers==0.0.15.dev0+ed99125.d20221213) (0.0.23)
  7. Requirement already satisfied: einops in f:\python 3.10.8\lib\site-packages (from xformers==0.0.15.dev0+ed99125.d20221213) (0.6.0)
  8. Requirement already satisfied: typing-extensions in f:\python 3.10.8\lib\site-packages (from pyre-extensions==0.0.23->xformers==0.0.15.dev0+ed99125.d20221213) (4.4.0)
  9. Requirement already satisfied: typing-inspect in f:\python 3.10.8\lib\site-packages (from pyre-extensions==0.0.23->xformers==0.0.15.dev0+ed99125.d20221213) (0.8.0)
  10. Requirement already satisfied: mypy-extensions>=0.3.0 in f:\python 3.10.8\lib\site-packages (from typing-inspect->pyre-extensions==0.0.23->xformers==0.0.15.dev0+ed99125.d20221213) (0.4.3)
  11. Installing collected packages: xformers
  12. Running setup.py develop for xformers
  13. error: subprocess-exited-with-error
  14.  
  15. × python setup.py develop did not run successfully.
  16. │ exit code: 1
  17. ╰─> [1841 lines of output]
  18. F:\Python 3.10.8\lib\site-packages\setuptools\dist.py:530: UserWarning: Normalizing '0.0.15.dev+ed99125.d20221213' to '0.0.15.dev0+ed99125.d20221213'
  19. warnings.warn(tmpl.format(**locals()))
  20. running develop
  21. F:\Python 3.10.8\lib\site-packages\setuptools\command\easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
  22. warnings.warn(
  23. F:\Python 3.10.8\lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
  24. warnings.warn(
  25. running egg_info
  26. writing xformers.egg-info\PKG-INFO
  27. writing dependency_links to xformers.egg-info\dependency_links.txt
  28. writing requirements to xformers.egg-info\requires.txt
  29. writing top-level names to xformers.egg-info\top_level.txt
  30. F:\Python 3.10.8\lib\site-packages\torch\utils\cpp_extension.py:476: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.
  31. warnings.warn(msg.format('we could not find ninja.'))
  32. reading manifest file 'xformers.egg-info\SOURCES.txt'
  33. reading manifest template 'MANIFEST.in'
  34. warning: manifest_maker: MANIFEST.in, line 3: path 'xformers/components/attention/csrc/' cannot end with '/'
  35.  
  36. warning: manifest_maker: MANIFEST.in, line 4: path 'third_party/sputnik/' cannot end with '/'
  37.  
  38. adding license file 'LICENSE'
  39. writing manifest file 'xformers.egg-info\SOURCES.txt'
  40. running build_ext
  41. F:\Python 3.10.8\lib\site-packages\torch\utils\cpp_extension.py:358: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  42. warnings.warn(f'Error checking compiler version for {compiler}: {error}')
  43. building 'xformers._C_flashattention' extension
  44. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\bin\HostX86\x64\cl.exe /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\cutlass\include "-IF:\Python 3.10.8\lib\site-packages\torch\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\TH" "-IF:\Python 3.10.8\lib\site-packages\torch\include\THC" "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" "-IF:\Python 3.10.8\include" "-IF:\Python 3.10.8\Include" -IG:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" /EHsc /TpF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/fmha_api.cpp /Fobuild\temp.win-amd64-cpython-310\Release\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/fmha_api.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc -O3 /MP /Zc:lambda /Zc:preprocessor -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C_flashattention -D_GLIBCXX_USE_CXX11_ABI=0
  45. cl : Command line warning D9002 : ignoring unknown option '-O3'
  46. fmha_api.cpp
  47. F:\Python 3.10.8\lib\site-packages\torch\include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  48. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  49. with
  50. [
  51. T=c10::SymInt
  52. ]
  53. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  54. with
  55. [
  56. T=c10::SymInt
  57. ]
  58. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  59. with
  60. [
  61. T=c10::SymInt
  62. ]
  63. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::SymInt>' being compiled
  64. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/TensorImpl.h(1580): note: see reference to class template instantiation 'c10::optional<c10::SymInt>' being compiled
  65. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  66. with
  67. [
  68. T=c10::SymInt
  69. ]
  70. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/TensorImpl.h(2688): warning C4805: '|': unsafe mix of type 'uintptr_t' and type 'bool' in operation
  71. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  72. with
  73. [
  74. T=at::TensorBase
  75. ]
  76. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  77. with
  78. [
  79. T=at::TensorBase
  80. ]
  81. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  82. with
  83. [
  84. T=at::TensorBase
  85. ]
  86. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::TensorBase>' being compiled
  87. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBase.h(933): note: see reference to class template instantiation 'c10::optional<at::TensorBase>' being compiled
  88. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  89. with
  90. [
  91. T=at::TensorBase
  92. ]
  93. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  94. with
  95. [
  96. T=at::Tensor
  97. ]
  98. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  99. with
  100. [
  101. T=at::Tensor
  102. ]
  103. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  104. with
  105. [
  106. T=at::Tensor
  107. ]
  108. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::Tensor>' being compiled
  109. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(512): note: see reference to class template instantiation 'c10::optional<at::Tensor>' being compiled
  110. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  111. with
  112. [
  113. T=at::Tensor
  114. ]
  115. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  116. with
  117. [
  118. T=at::Generator
  119. ]
  120. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  121. with
  122. [
  123. T=at::Generator
  124. ]
  125. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  126. with
  127. [
  128. T=at::Generator
  129. ]
  130. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::Generator>' being compiled
  131. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(589): note: see reference to class template instantiation 'c10::optional<at::Generator>' being compiled
  132. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  133. with
  134. [
  135. T=at::Generator
  136. ]
  137. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  138. with
  139. [
  140. T=c10::Scalar
  141. ]
  142. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  143. with
  144. [
  145. T=c10::Scalar
  146. ]
  147. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  148. with
  149. [
  150. T=c10::Scalar
  151. ]
  152. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::Scalar>' being compiled
  153. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(617): note: see reference to class template instantiation 'c10::optional<c10::Scalar>' being compiled
  154. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  155. with
  156. [
  157. T=c10::Scalar
  158. ]
  159. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  160. with
  161. [
  162. T=std::string
  163. ]
  164. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  165. with
  166. [
  167. T=std::string
  168. ]
  169. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  170. with
  171. [
  172. T=std::string
  173. ]
  174. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::string>' being compiled
  175. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type_base.h(450): note: see reference to class template instantiation 'c10::optional<std::string>' being compiled
  176. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  177. with
  178. [
  179. T=std::string
  180. ]
  181. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  182. with
  183. [
  184. T=c10::QualifiedName
  185. ]
  186. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  187. with
  188. [
  189. T=c10::QualifiedName
  190. ]
  191. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  192. with
  193. [
  194. T=c10::QualifiedName
  195. ]
  196. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::QualifiedName>' being compiled
  197. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type_base.h(698): note: see reference to class template instantiation 'c10::optional<c10::QualifiedName>' being compiled
  198. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  199. with
  200. [
  201. T=c10::QualifiedName
  202. ]
  203. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  204. with
  205. [
  206. T=std::shared_ptr<torch::jit::CompilationUnit>
  207. ]
  208. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  209. with
  210. [
  211. T=std::shared_ptr<torch::jit::CompilationUnit>
  212. ]
  213. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  214. with
  215. [
  216. T=std::shared_ptr<torch::jit::CompilationUnit>
  217. ]
  218. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::shared_ptr<torch::jit::CompilationUnit>>' being compiled
  219. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(1416): note: see reference to class template instantiation 'c10::optional<std::shared_ptr<torch::jit::CompilationUnit>>' being compiled
  220. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  221. with
  222. [
  223. T=std::shared_ptr<torch::jit::CompilationUnit>
  224. ]
  225. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  226. with
  227. [
  228. T=std::weak_ptr<torch::jit::CompilationUnit>
  229. ]
  230. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  231. with
  232. [
  233. T=std::weak_ptr<torch::jit::CompilationUnit>
  234. ]
  235. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  236. with
  237. [
  238. T=std::weak_ptr<torch::jit::CompilationUnit>
  239. ]
  240. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::weak_ptr<torch::jit::CompilationUnit>>' being compiled
  241. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(1417): note: see reference to class template instantiation 'c10::optional<std::weak_ptr<torch::jit::CompilationUnit>>' being compiled
  242. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  243. with
  244. [
  245. T=std::weak_ptr<torch::jit::CompilationUnit>
  246. ]
  247. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  248. with
  249. [
  250. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  251. ]
  252. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  253. with
  254. [
  255. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  256. ]
  257. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  258. with
  259. [
  260. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  261. ]
  262. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>>' being compiled
  263. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(483): note: see reference to class template instantiation 'c10::optional<std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>>' being compiled
  264. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  265. with
  266. [
  267. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  268. ]
  269. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  270. with
  271. [
  272. T=std::vector<bool,std::allocator<bool>>
  273. ]
  274. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  275. with
  276. [
  277. T=std::vector<bool,std::allocator<bool>>
  278. ]
  279. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  280. with
  281. [
  282. T=std::vector<bool,std::allocator<bool>>
  283. ]
  284. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<bool,std::allocator<bool>>>' being compiled
  285. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(442): note: see reference to class template instantiation 'c10::optional<std::vector<bool,std::allocator<bool>>>' being compiled
  286. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  287. with
  288. [
  289. T=std::vector<bool,std::allocator<bool>>
  290. ]
  291. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  292. with
  293. [
  294. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  295. ]
  296. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  297. with
  298. [
  299. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  300. ]
  301. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  302. with
  303. [
  304. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  305. ]
  306. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>>' being compiled
  307. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(568): note: see reference to class template instantiation 'c10::optional<std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>>' being compiled
  308. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(844): note: see reference to class template instantiation 'c10::VaryingShape<c10::Stride>' being compiled
  309. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  310. with
  311. [
  312. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  313. ]
  314. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  315. with
  316. [
  317. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  318. ]
  319. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  320. with
  321. [
  322. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  323. ]
  324. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  325. with
  326. [
  327. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  328. ]
  329. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>>' being compiled
  330. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(568): note: see reference to class template instantiation 'c10::optional<std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>>' being compiled
  331. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(614): note: see reference to class template instantiation 'c10::VaryingShape<int64_t>' being compiled
  332. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  333. with
  334. [
  335. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  336. ]
  337. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  338. with
  339. [
  340. T=std::vector<int64_t,std::allocator<int64_t>>
  341. ]
  342. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  343. with
  344. [
  345. T=std::vector<int64_t,std::allocator<int64_t>>
  346. ]
  347. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  348. with
  349. [
  350. T=std::vector<int64_t,std::allocator<int64_t>>
  351. ]
  352. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<int64_t,std::allocator<int64_t>>>' being compiled
  353. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(727): note: see reference to class template instantiation 'c10::optional<std::vector<int64_t,std::allocator<int64_t>>>' being compiled
  354. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  355. with
  356. [
  357. T=std::vector<int64_t,std::allocator<int64_t>>
  358. ]
  359. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  360. with
  361. [
  362. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  363. ]
  364. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  365. with
  366. [
  367. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  368. ]
  369. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  370. with
  371. [
  372. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  373. ]
  374. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  375. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  376. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/DeviceGuard.h(178): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::impl::VirtualGuardImpl>' being compiled
  377. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  378. with
  379. [
  380. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  381. ]
  382. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  383. with
  384. [
  385. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  386. ]
  387. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  388. with
  389. [
  390. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  391. ]
  392. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  393. with
  394. [
  395. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  396. ]
  397. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  398. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  399. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/StreamGuard.h(139): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  400. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  401. with
  402. [
  403. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  404. ]
  405. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  406. with
  407. [
  408. T=c10::impl::VirtualGuardImpl
  409. ]
  410. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  411. with
  412. [
  413. T=c10::impl::VirtualGuardImpl
  414. ]
  415. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  416. with
  417. [
  418. T=c10::impl::VirtualGuardImpl
  419. ]
  420. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::VirtualGuardImpl>' being compiled
  421. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  422. with
  423. [
  424. T=c10::impl::VirtualGuardImpl
  425. ]
  426. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/StreamGuard.h(162): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  427. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  428. with
  429. [
  430. T=c10::impl::VirtualGuardImpl
  431. ]
  432. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  433. with
  434. [
  435. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  436. ]
  437. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  438. with
  439. [
  440. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  441. ]
  442. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  443. with
  444. [
  445. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  446. ]
  447. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>>' being compiled
  448. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue_inl.h(853): note: see reference to class template instantiation 'c10::optional<std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>>' being compiled
  449. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  450. with
  451. [
  452. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  453. ]
  454. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  455. with
  456. [
  457. T=torch::autograd::ViewInfo
  458. ]
  459. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  460. with
  461. [
  462. T=torch::autograd::ViewInfo
  463. ]
  464. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  465. with
  466. [
  467. T=torch::autograd::ViewInfo
  468. ]
  469. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::autograd::ViewInfo>' being compiled
  470. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/variable.h(570): note: see reference to class template instantiation 'c10::optional<torch::autograd::ViewInfo>' being compiled
  471. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  472. with
  473. [
  474. T=torch::autograd::ViewInfo
  475. ]
  476. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  477. with
  478. [
  479. T=c10::IValue
  480. ]
  481. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  482. with
  483. [
  484. T=c10::IValue
  485. ]
  486. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  487. with
  488. [
  489. T=c10::IValue
  490. ]
  491. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::IValue>' being compiled
  492. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/function_schema.h(183): note: see reference to class template instantiation 'c10::optional<c10::IValue>' being compiled
  493. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  494. with
  495. [
  496. T=c10::IValue
  497. ]
  498. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  499. with
  500. [
  501. T=c10::AliasInfo
  502. ]
  503. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  504. with
  505. [
  506. T=c10::AliasInfo
  507. ]
  508. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  509. with
  510. [
  511. T=c10::AliasInfo
  512. ]
  513. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::AliasInfo>' being compiled
  514. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/function_schema.h(28): note: see reference to class template instantiation 'c10::optional<c10::AliasInfo>' being compiled
  515. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  516. with
  517. [
  518. T=c10::AliasInfo
  519. ]
  520. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  521. with
  522. [
  523. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  524. ]
  525. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  526. with
  527. [
  528. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  529. ]
  530. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  531. with
  532. [
  533. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  534. ]
  535. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<T,std::allocator<T>>>' being compiled
  536. with
  537. [
  538. T=c10::SymInt
  539. ]
  540. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(83): note: see reference to class template instantiation 'c10::optional<std::vector<T,std::allocator<T>>>' being compiled
  541. with
  542. [
  543. T=c10::SymInt
  544. ]
  545. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h(376): note: see reference to class template instantiation 'c10::OptionalArray<c10::SymInt>' being compiled
  546. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h(386): note: see reference to class template instantiation 'c10::impl::ivalue_to_arg<c10::OptionalArray<c10::SymInt>,AllowDeprecatedTypes>' being compiled
  547. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  548. with
  549. [
  550. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  551. ]
  552. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  553. with
  554. [
  555. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  556. ]
  557. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  558. with
  559. [
  560. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  561. ]
  562. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  563. with
  564. [
  565. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  566. ]
  567. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::either<c10::OperatorName,c10::FunctionSchema>>' being compiled
  568. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/op_registration/op_registration.h(434): note: see reference to class template instantiation 'c10::optional<c10::either<c10::OperatorName,c10::FunctionSchema>>' being compiled
  569. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  570. with
  571. [
  572. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  573. ]
  574. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  575. with
  576. [
  577. T=at::StepCallbacks
  578. ]
  579. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  580. with
  581. [
  582. T=at::StepCallbacks
  583. ]
  584. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  585. with
  586. [
  587. T=at::StepCallbacks
  588. ]
  589. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::StepCallbacks>' being compiled
  590. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/function.h(160): note: see reference to class template instantiation 'c10::optional<at::StepCallbacks>' being compiled
  591. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  592. with
  593. [
  594. T=at::StepCallbacks
  595. ]
  596. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  597. with
  598. [
  599. T=c10::DimVector
  600. ]
  601. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  602. with
  603. [
  604. T=c10::DimVector
  605. ]
  606. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  607. with
  608. [
  609. T=c10::DimVector
  610. ]
  611. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::DimVector>' being compiled
  612. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/TensorIterator.h(915): note: see reference to class template instantiation 'c10::optional<c10::DimVector>' being compiled
  613. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  614. with
  615. [
  616. T=c10::DimVector
  617. ]
  618. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  619. with
  620. [
  621. T=c10::impl::AnnotatedSchema
  622. ]
  623. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  624. with
  625. [
  626. T=c10::impl::AnnotatedSchema
  627. ]
  628. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  629. with
  630. [
  631. T=c10::impl::AnnotatedSchema
  632. ]
  633. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::AnnotatedSchema>' being compiled
  634. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/dispatch/OperatorEntry.h(223): note: see reference to class template instantiation 'c10::optional<c10::impl::AnnotatedSchema>' being compiled
  635. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  636. with
  637. [
  638. T=c10::impl::AnnotatedSchema
  639. ]
  640. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  641. with
  642. [
  643. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  644. ]
  645. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  646. with
  647. [
  648. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  649. ]
  650. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  651. with
  652. [
  653. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  654. ]
  655. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::OperatorEntry::CppSignatureWithDebug>' being compiled
  656. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/dispatch/OperatorEntry.h(286): note: see reference to class template instantiation 'c10::optional<c10::impl::OperatorEntry::CppSignatureWithDebug>' being compiled
  657. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  658. with
  659. [
  660. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  661. ]
  662. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  663. with
  664. [
  665. T=std::tuple<std::string,size_t,size_t>
  666. ]
  667. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  668. with
  669. [
  670. T=std::tuple<std::string,size_t,size_t>
  671. ]
  672. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  673. with
  674. [
  675. T=std::tuple<std::string,size_t,size_t>
  676. ]
  677. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::tuple<std::string,size_t,size_t>>' being compiled
  678. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/frontend/source_range.h(357): note: see reference to class template instantiation 'c10::optional<std::tuple<std::string,size_t,size_t>>' being compiled
  679. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  680. with
  681. [
  682. T=std::tuple<std::string,size_t,size_t>
  683. ]
  684. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  685. with
  686. [
  687. T=torch::jit::SourceRange
  688. ]
  689. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  690. with
  691. [
  692. T=torch::jit::SourceRange
  693. ]
  694. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  695. with
  696. [
  697. T=torch::jit::SourceRange
  698. ]
  699. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::SourceRange>' being compiled
  700. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/frontend/source_range.h(380): note: see reference to class template instantiation 'c10::optional<torch::jit::SourceRange>' being compiled
  701. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  702. with
  703. [
  704. T=torch::jit::SourceRange
  705. ]
  706. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  707. with
  708. [
  709. T=torch::jit::InlinedCallStackPtr
  710. ]
  711. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  712. with
  713. [
  714. T=torch::jit::InlinedCallStackPtr
  715. ]
  716. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  717. with
  718. [
  719. T=torch::jit::InlinedCallStackPtr
  720. ]
  721. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::InlinedCallStackPtr>' being compiled
  722. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/scope.h(127): note: see reference to class template instantiation 'c10::optional<torch::jit::InlinedCallStackPtr>' being compiled
  723. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  724. with
  725. [
  726. T=torch::jit::InlinedCallStackPtr
  727. ]
  728. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  729. with
  730. [
  731. T=torch::jit::ModuleInstanceInfo
  732. ]
  733. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  734. with
  735. [
  736. T=torch::jit::ModuleInstanceInfo
  737. ]
  738. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  739. with
  740. [
  741. T=torch::jit::ModuleInstanceInfo
  742. ]
  743. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::ModuleInstanceInfo>' being compiled
  744. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/scope.h(140): note: see reference to class template instantiation 'c10::optional<torch::jit::ModuleInstanceInfo>' being compiled
  745. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  746. with
  747. [
  748. T=torch::jit::ModuleInstanceInfo
  749. ]
  750. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  751. with
  752. [
  753. T=torch::jit::ScopePtr
  754. ]
  755. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  756. with
  757. [
  758. T=torch::jit::ScopePtr
  759. ]
  760. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  761. with
  762. [
  763. T=torch::jit::ScopePtr
  764. ]
  765. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::ScopePtr>' being compiled
  766. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/constants.h(29): note: see reference to class template instantiation 'c10::optional<torch::jit::ScopePtr>' being compiled
  767. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  768. with
  769. [
  770. T=torch::jit::ScopePtr
  771. ]
  772. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  773. with
  774. [
  775. T=at::ThreadLocalState
  776. ]
  777. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  778. with
  779. [
  780. T=at::ThreadLocalState
  781. ]
  782. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  783. with
  784. [
  785. T=at::ThreadLocalState
  786. ]
  787. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::ThreadLocalState>' being compiled
  788. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/runtime/interpreter.h(150): note: see reference to class template instantiation 'c10::optional<at::ThreadLocalState>' being compiled
  789. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  790. with
  791. [
  792. T=at::ThreadLocalState
  793. ]
  794. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  795. with
  796. [
  797. T=std::shared_ptr<torch::jit::Graph>
  798. ]
  799. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  800. with
  801. [
  802. T=std::shared_ptr<torch::jit::Graph>
  803. ]
  804. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  805. with
  806. [
  807. T=std::shared_ptr<torch::jit::Graph>
  808. ]
  809. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::shared_ptr<torch::jit::Graph>>' being compiled
  810. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include\array(597): note: see reference to class template instantiation 'c10::optional<std::shared_ptr<torch::jit::Graph>>' being compiled
  811. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/function_impl.h(165): note: see reference to class template instantiation 'std::array<c10::optional<std::shared_ptr<torch::jit::Graph>>,4>' being compiled
  812. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  813. with
  814. [
  815. T=std::shared_ptr<torch::jit::Graph>
  816. ]
  817. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  818. with
  819. [
  820. T=torch::jit::GraphExecutor
  821. ]
  822. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  823. with
  824. [
  825. T=torch::jit::GraphExecutor
  826. ]
  827. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  828. with
  829. [
  830. T=torch::jit::GraphExecutor
  831. ]
  832. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::GraphExecutor>' being compiled
  833. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include\array(597): note: see reference to class template instantiation 'c10::optional<torch::jit::GraphExecutor>' being compiled
  834. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/function_impl.h(179): note: see reference to class template instantiation 'std::array<c10::optional<torch::jit::GraphExecutor>,4>' being compiled
  835. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  836. with
  837. [
  838. T=torch::jit::GraphExecutor
  839. ]
  840. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  841. with
  842. [
  843. T=torch::jit::Method
  844. ]
  845. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  846. with
  847. [
  848. T=torch::jit::Method
  849. ]
  850. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  851. with
  852. [
  853. T=torch::jit::Method
  854. ]
  855. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::Method>' being compiled
  856. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/object.h(46): note: see reference to class template instantiation 'c10::optional<torch::jit::Method>' being compiled
  857. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  858. with
  859. [
  860. T=torch::jit::Method
  861. ]
  862. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  863. with
  864. [
  865. T=std::vector<std::string,std::allocator<std::string>>
  866. ]
  867. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  868. with
  869. [
  870. T=std::vector<std::string,std::allocator<std::string>>
  871. ]
  872. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  873. with
  874. [
  875. T=std::vector<std::string,std::allocator<std::string>>
  876. ]
  877. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<std::string,std::allocator<std::string>>>' being compiled
  878. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/module.h(304): note: see reference to class template instantiation 'c10::optional<std::vector<std::string,std::allocator<std::string>>>' being compiled
  879. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  880. with
  881. [
  882. T=std::vector<std::string,std::allocator<std::string>>
  883. ]
  884. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  885. with
  886. [
  887. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  888. ]
  889. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  890. with
  891. [
  892. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  893. ]
  894. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  895. with
  896. [
  897. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  898. ]
  899. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>' being compiled
  900. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/profiler_legacy.h(410): note: see reference to class template instantiation 'c10::optional<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>' being compiled
  901. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  902. with
  903. [
  904. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  905. ]
  906. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  907. with
  908. [
  909. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  910. ]
  911. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  912. with
  913. [
  914. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  915. ]
  916. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  917. with
  918. [
  919. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  920. ]
  921. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>' being compiled
  922. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/loss.h(453): note: see reference to class template instantiation 'c10::optional<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>' being compiled
  923. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  924. with
  925. [
  926. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  927. ]
  928. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  929. with
  930. [
  931. T=std::vector<double,std::allocator<double>>
  932. ]
  933. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  934. with
  935. [
  936. T=std::vector<double,std::allocator<double>>
  937. ]
  938. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  939. with
  940. [
  941. T=std::vector<double,std::allocator<double>>
  942. ]
  943. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<T,std::allocator<T>>>' being compiled
  944. with
  945. [
  946. T=double
  947. ]
  948. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/upsampling.h(27): note: see reference to class template instantiation 'c10::optional<std::vector<T,std::allocator<T>>>' being compiled
  949. with
  950. [
  951. T=double
  952. ]
  953. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  954. with
  955. [
  956. T=std::vector<double,std::allocator<double>>
  957. ]
  958. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  959. with
  960. [
  961. T=std::tuple<at::Tensor,at::Tensor>
  962. ]
  963. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  964. with
  965. [
  966. T=std::tuple<at::Tensor,at::Tensor>
  967. ]
  968. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  969. with
  970. [
  971. T=std::tuple<at::Tensor,at::Tensor>
  972. ]
  973. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::tuple<at::Tensor,at::Tensor>>' being compiled
  974. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/modules/rnn.h(165): note: see reference to class template instantiation 'c10::optional<std::tuple<at::Tensor,at::Tensor>>' being compiled
  975. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  976. with
  977. [
  978. T=std::tuple<at::Tensor,at::Tensor>
  979. ]
  980. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  981. with
  982. [
  983. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  984. ]
  985. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  986. with
  987. [
  988. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  989. ]
  990. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  991. with
  992. [
  993. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  994. ]
  995. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<at::Tensor,std::allocator<at::Tensor>>>' being compiled
  996. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/optim/lbfgs.h(50): note: see reference to class template instantiation 'c10::optional<std::vector<at::Tensor,std::allocator<at::Tensor>>>' being compiled
  997. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  998. with
  999. [
  1000. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  1001. ]
  1002. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1003. with
  1004. [
  1005. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1006. ]
  1007. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1008. with
  1009. [
  1010. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1011. ]
  1012. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1013. with
  1014. [
  1015. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1016. ]
  1017. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1018. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1019. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(140): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1020. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1021. with
  1022. [
  1023. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1024. ]
  1025. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1026. with
  1027. [
  1028. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1029. ]
  1030. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1031. with
  1032. [
  1033. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1034. ]
  1035. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1036. with
  1037. [
  1038. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1039. ]
  1040. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1041. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1042. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(273): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1043. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1044. with
  1045. [
  1046. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1047. ]
  1048. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1049. with
  1050. [
  1051. T=c10::cuda::impl::CUDAGuardImpl
  1052. ]
  1053. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1054. with
  1055. [
  1056. T=c10::cuda::impl::CUDAGuardImpl
  1057. ]
  1058. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1059. with
  1060. [
  1061. T=c10::cuda::impl::CUDAGuardImpl
  1062. ]
  1063. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1064. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  1065. with
  1066. [
  1067. T=c10::cuda::impl::CUDAGuardImpl
  1068. ]
  1069. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(292): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1070. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1071. with
  1072. [
  1073. T=c10::cuda::impl::CUDAGuardImpl
  1074. ]
  1075. "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin\nvcc" -c F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/src/fmha_block_dgrad_fp16_kernel_loop.sm80.cu -o build\temp.win-amd64-cpython-310\Release\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/src/fmha_block_dgrad_fp16_kernel_loop.sm80.obj -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\cutlass\include "-IF:\Python 3.10.8\lib\site-packages\torch\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\TH" "-IF:\Python 3.10.8\lib\site-packages\torch\include\THC" "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" "-IF:\Python 3.10.8\include" "-IF:\Python 3.10.8\Include" -IG:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DHAS_PYTORCH --use_fast_math -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --extended-lambda --generate-line-info -DNDEBUG --threads 4 --ptxas-options=-v -std=c++17 -Xcompiler /Zc:lambda -Xcompiler /Zc:preprocessor -O3 --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -std=c++17 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_86,code=sm_86 --generate-line-info -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C_flashattention -D_GLIBCXX_USE_CXX11_ABI=0 --use-local-env
  1076. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  1077. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  1078. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  1079. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  1080. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  1081. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  1082. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  1083. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  1084. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  1085. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  1086. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  1087. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  1088. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  1089. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  1090. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  1091. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  1092. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  1093. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  1094.  
  1095. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1096. detected during:
  1097. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1098. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1099. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1100. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1101. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1102. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1103. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1104. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1105. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1106. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  1107.  
  1108. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1109. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1110. (56): here
  1111.  
  1112. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1113. detected during:
  1114. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1115. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1116. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1117. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1118. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1119. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1120. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1121. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1122. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1123. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  1124.  
  1125. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1126. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1127. (59): here
  1128.  
  1129. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1130. detected during:
  1131. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1132. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1133. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1134. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1135. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1136. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1137. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1138. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1139. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1140. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  1141.  
  1142. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1143. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1144. (62): here
  1145.  
  1146. ptxas info : 25 bytes gmem
  1147. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1148. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1149. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1150. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1151. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1152. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1153. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1154. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1155. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1156. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1157. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1158. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1159. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1160. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1161. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1162. ptxas info : Used 253 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1163. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1164. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1165. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1166. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1167. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1168. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1169. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1170. ptxas info : Used 251 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1171. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1172. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1173. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1174. ptxas info : Used 244 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1175. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1176. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1177. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1178. ptxas info : Used 240 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1179. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1180. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1181. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1182. ptxas info : Used 253 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1183. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1184. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1185. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1186. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1187. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1188. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1189. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1190. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1191. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1192. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1193. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1194. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1195. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1196. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1197. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1198. ptxas info : Used 239 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1199. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1200. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1201. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1202. ptxas info : Used 245 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1203. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1204. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1205. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1206. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1207. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1208. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1209. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1210. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1211. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1212. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1213. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1214. ptxas info : Used 221 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1215. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1216. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1217. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1218. ptxas info : Used 223 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1219. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1220. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1221. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1222. ptxas info : Used 235 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1223. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1224. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1225. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1226. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1227. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1228. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1229. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1230. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1231. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1232. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1233. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1234. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1235. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1236. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1237. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1238. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1239. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1240. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1241. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1242. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1243. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1244. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1245. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1246. ptxas info : Used 194 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1247. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1248. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1249. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1250. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1251. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1252. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1253. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1254. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1255. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  1256. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1257. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1258. ptxas info : Used 228 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1259. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1260. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1261. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1262. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1263. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1264. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1265. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1266. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1267. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1268. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1269. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1270. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1271. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  1272. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1273. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1274. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1275. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1276. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1277. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1278. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1279. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1280. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1281. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1282. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1283. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1284. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1285. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1286. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1287. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  1288. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1289. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1290. ptxas info : Used 232 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1291. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  1292.  
  1293. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1294. detected during:
  1295. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1296. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1297. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1298. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1299. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1300. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1301. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1302. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1303. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1304. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  1305.  
  1306. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1307. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1308. (56): here
  1309.  
  1310. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1311. detected during:
  1312. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1313. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1314. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1315. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1316. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1317. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1318. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1319. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1320. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1321. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  1322.  
  1323. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1324. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1325. (59): here
  1326.  
  1327. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1328. detected during:
  1329. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1330. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1331. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1332. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1333. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1334. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1335. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1336. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1337. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1338. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  1339.  
  1340. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1341. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1342. (62): here
  1343.  
  1344. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  1345.  
  1346. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1347. detected during:
  1348. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1349. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1350. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1351. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1352. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1353. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1354. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1355. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1356. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1357. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  1358.  
  1359. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1360. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  1361. (56): here
  1362.  
  1363. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1364. detected during:
  1365. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1366. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1367. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1368. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1369. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1370. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1371. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1372. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1373. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1374. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  1375.  
  1376. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1377. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  1378. (59): here
  1379.  
  1380. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  1381. detected during:
  1382. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  1383. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  1384. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  1385. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  1386. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  1387. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  1388. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  1389. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  1390. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1391. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  1392.  
  1393. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  1394. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  1395. (62): here
  1396.  
  1397. ptxas info : 25 bytes gmem
  1398. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1399. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1400. 8 bytes stack frame, 4 bytes spill stores, 4 bytes spill loads
  1401. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1402. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1403. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1404. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1405. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1406. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1407. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1408. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1409. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1410. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1411. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1412. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1413. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1414. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1415. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1416. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1417. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1418. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1419. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1420. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1421. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1422. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1423. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1424. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1425. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1426. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1427. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1428. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1429. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1430. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1431. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1432. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1433. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1434. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1435. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1436. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1437. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1438. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1439. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1440. 8 bytes stack frame, 4 bytes spill stores, 4 bytes spill loads
  1441. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1442. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1443. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1444. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1445. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1446. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1447. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1448. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1449. ptxas info : Used 239 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1450. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1451. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1452. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1453. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1454. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1455. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1456. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1457. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1458. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1459. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1460. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1461. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1462. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1463. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1464. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1465. ptxas info : Used 221 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1466. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1467. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1468. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1469. ptxas info : Used 223 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1470. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1471. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1472. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1473. ptxas info : Used 235 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1474. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1475. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1476. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1477. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1478. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1479. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1480. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1481. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1482. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1483. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1484. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1485. ptxas info : Used 241 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1486. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1487. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1488. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1489. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1490. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1491. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1492. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1493. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1494. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1495. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1496. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1497. ptxas info : Used 195 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1498. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1499. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1500. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1501. ptxas info : Used 209 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1502. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1503. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1504. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1505. ptxas info : Used 218 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1506. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  1507. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1508. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1509. ptxas info : Used 222 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1510. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1511. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1512. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1513. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1514. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1515. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1516. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1517. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1518. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1519. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1520. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1521. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1522. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  1523. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1524. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1525. ptxas info : Used 200 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1526. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1527. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1528. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1529. ptxas info : Used 209 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1530. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1531. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1532. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1533. ptxas info : Used 213 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1534. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1535. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1536. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1537. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1538. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  1539. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1540. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1541. ptxas info : Used 233 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1542. ptxas info : 25 bytes gmem
  1543. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1544. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1545. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1546. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1547. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1548. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1549. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1550. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1551. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1552. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1553. 24 bytes stack frame, 28 bytes spill stores, 24 bytes spill loads
  1554. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1555. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1556. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1557. 32 bytes stack frame, 48 bytes spill stores, 36 bytes spill loads
  1558. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1559. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1560. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1561. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1562. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1563. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1564. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1565. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1566. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1567. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1568. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1569. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1570. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1571. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1572. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1573. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  1574. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1575. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1576. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1577. 32 bytes stack frame, 52 bytes spill stores, 36 bytes spill loads
  1578. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1579. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1580. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1581. 40 bytes stack frame, 44 bytes spill stores, 36 bytes spill loads
  1582. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1583. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1584. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1585. 32 bytes stack frame, 60 bytes spill stores, 56 bytes spill loads
  1586. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1587. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1588. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1589. 40 bytes stack frame, 84 bytes spill stores, 72 bytes spill loads
  1590. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1591. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1592. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1593. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1594. ptxas info : Used 248 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1595. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1596. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1597. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1598. ptxas info : Used 245 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1599. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1600. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1601. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1602. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1603. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1604. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1605. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1606. ptxas info : Used 249 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1607. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1608. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1609. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1610. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1611. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1612. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1613. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1614. ptxas info : Used 216 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1615. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1616. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1617. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1618. ptxas info : Used 232 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1619. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1620. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1621. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1622. ptxas info : Used 224 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1623. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1624. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1625. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1626. ptxas info : Used 243 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1627. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1628. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1629. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1630. ptxas info : Used 249 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1631. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1632. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1633. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1634. ptxas info : Used 244 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1635. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1636. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1637. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1638. ptxas info : Used 251 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1639. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1640. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  1641. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1642. ptxas info : Used 204 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1643. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1644. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  1645. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1646. ptxas info : Used 218 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1647. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1648. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  1649. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1650. ptxas info : Used 220 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1651. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  1652. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  1653. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1654. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1655. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1656. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  1657. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1658. ptxas info : Used 170 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1659. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1660. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  1661. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1662. ptxas info : Used 186 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1663. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1664. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  1665. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1666. ptxas info : Used 202 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1667. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  1668. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  1669. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1670. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1671. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1672. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  1673. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1674. ptxas info : Used 216 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1675. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1676. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  1677. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1678. ptxas info : Used 220 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1679. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1680. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  1681. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1682. ptxas info : Used 229 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1683. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  1684. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  1685. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  1686. ptxas info : Used 237 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  1687. tmpxft_00001a64_00000000-7_fmha_block_dgrad_fp16_kernel_loop.sm80.compute_86.cudafe1.cpp
  1688. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1689. with
  1690. [
  1691. T=c10::SymInt
  1692. ]
  1693. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1694. with
  1695. [
  1696. T=c10::SymInt
  1697. ]
  1698. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1699. with
  1700. [
  1701. T=c10::SymInt
  1702. ]
  1703. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::SymInt>' being compiled
  1704. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/TensorImpl.h(1577): note: see reference to class template instantiation 'c10::optional<c10::SymInt>' being compiled
  1705. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1706. with
  1707. [
  1708. T=c10::SymInt
  1709. ]
  1710. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/TensorImpl.h(2687): warning C4805: '|': unsafe mix of type 'uintptr_t' and type 'bool' in operation
  1711. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1712. with
  1713. [
  1714. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  1715. ]
  1716. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1717. with
  1718. [
  1719. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  1720. ]
  1721. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1722. with
  1723. [
  1724. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  1725. ]
  1726. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  1727. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  1728. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/DeviceGuard.h(178): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::impl::VirtualGuardImpl>' being compiled
  1729. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1730. with
  1731. [
  1732. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  1733. ]
  1734. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1735. with
  1736. [
  1737. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1738. ]
  1739. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1740. with
  1741. [
  1742. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1743. ]
  1744. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1745. with
  1746. [
  1747. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1748. ]
  1749. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1750. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1751. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(140): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1752. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1753. with
  1754. [
  1755. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  1756. ]
  1757. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1758. with
  1759. [
  1760. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1761. ]
  1762. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1763. with
  1764. [
  1765. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1766. ]
  1767. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1768. with
  1769. [
  1770. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1771. ]
  1772. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1773. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  1774. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(273): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1775. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1776. with
  1777. [
  1778. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  1779. ]
  1780. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1781. with
  1782. [
  1783. T=c10::cuda::impl::CUDAGuardImpl
  1784. ]
  1785. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1786. with
  1787. [
  1788. T=c10::cuda::impl::CUDAGuardImpl
  1789. ]
  1790. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1791. with
  1792. [
  1793. T=c10::cuda::impl::CUDAGuardImpl
  1794. ]
  1795. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1796. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  1797. with
  1798. [
  1799. T=c10::cuda::impl::CUDAGuardImpl
  1800. ]
  1801. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(292): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  1802. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1803. with
  1804. [
  1805. T=c10::cuda::impl::CUDAGuardImpl
  1806. ]
  1807. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1808. with
  1809. [
  1810. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  1811. ]
  1812. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1813. with
  1814. [
  1815. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  1816. ]
  1817. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1818. with
  1819. [
  1820. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  1821. ]
  1822. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  1823. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  1824. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/StreamGuard.h(139): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  1825. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1826. with
  1827. [
  1828. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  1829. ]
  1830. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1831. with
  1832. [
  1833. T=c10::impl::VirtualGuardImpl
  1834. ]
  1835. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1836. with
  1837. [
  1838. T=c10::impl::VirtualGuardImpl
  1839. ]
  1840. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1841. with
  1842. [
  1843. T=c10::impl::VirtualGuardImpl
  1844. ]
  1845. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::VirtualGuardImpl>' being compiled
  1846. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  1847. with
  1848. [
  1849. T=c10::impl::VirtualGuardImpl
  1850. ]
  1851. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/StreamGuard.h(162): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  1852. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1853. with
  1854. [
  1855. T=c10::impl::VirtualGuardImpl
  1856. ]
  1857. C:\Users\User\AppData\Local\Temp\tmpxft_00001a64_00000000-7_fmha_block_dgrad_fp16_kernel_loop.sm80.compute_86.cudafe1.cpp : fatal error C1083: Cannot open compiler generated file: '': Invalid argument
  1858. error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin\\nvcc.exe' failed with exit code 4294967295
  1859. [end of output]
  1860.  
  1861. note: This error originates from a subprocess, and is likely not a problem with pip.
  1862. error: subprocess-exited-with-error
  1863.  
  1864. × python setup.py develop did not run successfully.
  1865. │ exit code: 1
  1866. ╰─> [1841 lines of output]
  1867. F:\Python 3.10.8\lib\site-packages\setuptools\dist.py:530: UserWarning: Normalizing '0.0.15.dev+ed99125.d20221213' to '0.0.15.dev0+ed99125.d20221213'
  1868. warnings.warn(tmpl.format(**locals()))
  1869. running develop
  1870. F:\Python 3.10.8\lib\site-packages\setuptools\command\easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
  1871. warnings.warn(
  1872. F:\Python 3.10.8\lib\site-packages\setuptools\command\install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
  1873. warnings.warn(
  1874. running egg_info
  1875. writing xformers.egg-info\PKG-INFO
  1876. writing dependency_links to xformers.egg-info\dependency_links.txt
  1877. writing requirements to xformers.egg-info\requires.txt
  1878. writing top-level names to xformers.egg-info\top_level.txt
  1879. F:\Python 3.10.8\lib\site-packages\torch\utils\cpp_extension.py:476: UserWarning: Attempted to use ninja as the BuildExtension backend but we could not find ninja.. Falling back to using the slow distutils backend.
  1880. warnings.warn(msg.format('we could not find ninja.'))
  1881. reading manifest file 'xformers.egg-info\SOURCES.txt'
  1882. reading manifest template 'MANIFEST.in'
  1883. warning: manifest_maker: MANIFEST.in, line 3: path 'xformers/components/attention/csrc/' cannot end with '/'
  1884.  
  1885. warning: manifest_maker: MANIFEST.in, line 4: path 'third_party/sputnik/' cannot end with '/'
  1886.  
  1887. adding license file 'LICENSE'
  1888. writing manifest file 'xformers.egg-info\SOURCES.txt'
  1889. running build_ext
  1890. F:\Python 3.10.8\lib\site-packages\torch\utils\cpp_extension.py:358: UserWarning: Error checking compiler version for cl: [WinError 2] The system cannot find the file specified
  1891. warnings.warn(f'Error checking compiler version for {compiler}: {error}')
  1892. building 'xformers._C_flashattention' extension
  1893. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\bin\HostX86\x64\cl.exe /c /nologo /O2 /W3 /GL /DNDEBUG /MD -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\cutlass\include "-IF:\Python 3.10.8\lib\site-packages\torch\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\TH" "-IF:\Python 3.10.8\lib\site-packages\torch\include\THC" "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" "-IF:\Python 3.10.8\include" "-IF:\Python 3.10.8\Include" -IG:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" /EHsc /TpF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/fmha_api.cpp /Fobuild\temp.win-amd64-cpython-310\Release\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/fmha_api.obj /MD /wd4819 /wd4251 /wd4244 /wd4267 /wd4275 /wd4018 /wd4190 /EHsc -O3 /MP /Zc:lambda /Zc:preprocessor -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C_flashattention -D_GLIBCXX_USE_CXX11_ABI=0
  1894. cl : Command line warning D9002 : ignoring unknown option '-O3'
  1895. fmha_api.cpp
  1896. F:\Python 3.10.8\lib\site-packages\torch\include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  1897. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1898. with
  1899. [
  1900. T=c10::SymInt
  1901. ]
  1902. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1903. with
  1904. [
  1905. T=c10::SymInt
  1906. ]
  1907. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1908. with
  1909. [
  1910. T=c10::SymInt
  1911. ]
  1912. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::SymInt>' being compiled
  1913. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/TensorImpl.h(1580): note: see reference to class template instantiation 'c10::optional<c10::SymInt>' being compiled
  1914. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1915. with
  1916. [
  1917. T=c10::SymInt
  1918. ]
  1919. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/TensorImpl.h(2688): warning C4805: '|': unsafe mix of type 'uintptr_t' and type 'bool' in operation
  1920. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1921. with
  1922. [
  1923. T=at::TensorBase
  1924. ]
  1925. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1926. with
  1927. [
  1928. T=at::TensorBase
  1929. ]
  1930. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1931. with
  1932. [
  1933. T=at::TensorBase
  1934. ]
  1935. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::TensorBase>' being compiled
  1936. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBase.h(933): note: see reference to class template instantiation 'c10::optional<at::TensorBase>' being compiled
  1937. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1938. with
  1939. [
  1940. T=at::TensorBase
  1941. ]
  1942. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1943. with
  1944. [
  1945. T=at::Tensor
  1946. ]
  1947. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1948. with
  1949. [
  1950. T=at::Tensor
  1951. ]
  1952. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1953. with
  1954. [
  1955. T=at::Tensor
  1956. ]
  1957. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::Tensor>' being compiled
  1958. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(512): note: see reference to class template instantiation 'c10::optional<at::Tensor>' being compiled
  1959. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1960. with
  1961. [
  1962. T=at::Tensor
  1963. ]
  1964. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1965. with
  1966. [
  1967. T=at::Generator
  1968. ]
  1969. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1970. with
  1971. [
  1972. T=at::Generator
  1973. ]
  1974. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1975. with
  1976. [
  1977. T=at::Generator
  1978. ]
  1979. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::Generator>' being compiled
  1980. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(589): note: see reference to class template instantiation 'c10::optional<at::Generator>' being compiled
  1981. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  1982. with
  1983. [
  1984. T=at::Generator
  1985. ]
  1986. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  1987. with
  1988. [
  1989. T=c10::Scalar
  1990. ]
  1991. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  1992. with
  1993. [
  1994. T=c10::Scalar
  1995. ]
  1996. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  1997. with
  1998. [
  1999. T=c10::Scalar
  2000. ]
  2001. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::Scalar>' being compiled
  2002. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/TensorBody.h(617): note: see reference to class template instantiation 'c10::optional<c10::Scalar>' being compiled
  2003. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2004. with
  2005. [
  2006. T=c10::Scalar
  2007. ]
  2008. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2009. with
  2010. [
  2011. T=std::string
  2012. ]
  2013. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2014. with
  2015. [
  2016. T=std::string
  2017. ]
  2018. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2019. with
  2020. [
  2021. T=std::string
  2022. ]
  2023. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::string>' being compiled
  2024. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type_base.h(450): note: see reference to class template instantiation 'c10::optional<std::string>' being compiled
  2025. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2026. with
  2027. [
  2028. T=std::string
  2029. ]
  2030. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2031. with
  2032. [
  2033. T=c10::QualifiedName
  2034. ]
  2035. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2036. with
  2037. [
  2038. T=c10::QualifiedName
  2039. ]
  2040. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2041. with
  2042. [
  2043. T=c10::QualifiedName
  2044. ]
  2045. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::QualifiedName>' being compiled
  2046. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type_base.h(698): note: see reference to class template instantiation 'c10::optional<c10::QualifiedName>' being compiled
  2047. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2048. with
  2049. [
  2050. T=c10::QualifiedName
  2051. ]
  2052. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2053. with
  2054. [
  2055. T=std::shared_ptr<torch::jit::CompilationUnit>
  2056. ]
  2057. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2058. with
  2059. [
  2060. T=std::shared_ptr<torch::jit::CompilationUnit>
  2061. ]
  2062. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2063. with
  2064. [
  2065. T=std::shared_ptr<torch::jit::CompilationUnit>
  2066. ]
  2067. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::shared_ptr<torch::jit::CompilationUnit>>' being compiled
  2068. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(1416): note: see reference to class template instantiation 'c10::optional<std::shared_ptr<torch::jit::CompilationUnit>>' being compiled
  2069. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2070. with
  2071. [
  2072. T=std::shared_ptr<torch::jit::CompilationUnit>
  2073. ]
  2074. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2075. with
  2076. [
  2077. T=std::weak_ptr<torch::jit::CompilationUnit>
  2078. ]
  2079. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2080. with
  2081. [
  2082. T=std::weak_ptr<torch::jit::CompilationUnit>
  2083. ]
  2084. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2085. with
  2086. [
  2087. T=std::weak_ptr<torch::jit::CompilationUnit>
  2088. ]
  2089. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::weak_ptr<torch::jit::CompilationUnit>>' being compiled
  2090. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(1417): note: see reference to class template instantiation 'c10::optional<std::weak_ptr<torch::jit::CompilationUnit>>' being compiled
  2091. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2092. with
  2093. [
  2094. T=std::weak_ptr<torch::jit::CompilationUnit>
  2095. ]
  2096. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2097. with
  2098. [
  2099. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  2100. ]
  2101. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2102. with
  2103. [
  2104. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  2105. ]
  2106. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2107. with
  2108. [
  2109. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  2110. ]
  2111. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>>' being compiled
  2112. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(483): note: see reference to class template instantiation 'c10::optional<std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>>' being compiled
  2113. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2114. with
  2115. [
  2116. T=std::vector<c10::ShapeSymbol,std::allocator<c10::ShapeSymbol>>
  2117. ]
  2118. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2119. with
  2120. [
  2121. T=std::vector<bool,std::allocator<bool>>
  2122. ]
  2123. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2124. with
  2125. [
  2126. T=std::vector<bool,std::allocator<bool>>
  2127. ]
  2128. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2129. with
  2130. [
  2131. T=std::vector<bool,std::allocator<bool>>
  2132. ]
  2133. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<bool,std::allocator<bool>>>' being compiled
  2134. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(442): note: see reference to class template instantiation 'c10::optional<std::vector<bool,std::allocator<bool>>>' being compiled
  2135. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2136. with
  2137. [
  2138. T=std::vector<bool,std::allocator<bool>>
  2139. ]
  2140. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2141. with
  2142. [
  2143. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  2144. ]
  2145. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2146. with
  2147. [
  2148. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  2149. ]
  2150. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2151. with
  2152. [
  2153. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  2154. ]
  2155. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>>' being compiled
  2156. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(568): note: see reference to class template instantiation 'c10::optional<std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>>' being compiled
  2157. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(844): note: see reference to class template instantiation 'c10::VaryingShape<c10::Stride>' being compiled
  2158. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2159. with
  2160. [
  2161. T=std::vector<c10::optional<c10::Stride>,std::allocator<c10::optional<c10::Stride>>>
  2162. ]
  2163. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2164. with
  2165. [
  2166. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  2167. ]
  2168. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2169. with
  2170. [
  2171. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  2172. ]
  2173. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2174. with
  2175. [
  2176. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  2177. ]
  2178. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>>' being compiled
  2179. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(568): note: see reference to class template instantiation 'c10::optional<std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>>' being compiled
  2180. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(614): note: see reference to class template instantiation 'c10::VaryingShape<int64_t>' being compiled
  2181. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2182. with
  2183. [
  2184. T=std::vector<c10::optional<int64_t>,std::allocator<c10::optional<int64_t>>>
  2185. ]
  2186. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2187. with
  2188. [
  2189. T=std::vector<int64_t,std::allocator<int64_t>>
  2190. ]
  2191. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2192. with
  2193. [
  2194. T=std::vector<int64_t,std::allocator<int64_t>>
  2195. ]
  2196. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2197. with
  2198. [
  2199. T=std::vector<int64_t,std::allocator<int64_t>>
  2200. ]
  2201. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<int64_t,std::allocator<int64_t>>>' being compiled
  2202. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/jit_type.h(727): note: see reference to class template instantiation 'c10::optional<std::vector<int64_t,std::allocator<int64_t>>>' being compiled
  2203. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2204. with
  2205. [
  2206. T=std::vector<int64_t,std::allocator<int64_t>>
  2207. ]
  2208. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2209. with
  2210. [
  2211. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  2212. ]
  2213. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2214. with
  2215. [
  2216. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  2217. ]
  2218. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2219. with
  2220. [
  2221. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  2222. ]
  2223. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  2224. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  2225. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/DeviceGuard.h(178): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::impl::VirtualGuardImpl>' being compiled
  2226. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2227. with
  2228. [
  2229. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  2230. ]
  2231. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2232. with
  2233. [
  2234. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  2235. ]
  2236. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2237. with
  2238. [
  2239. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  2240. ]
  2241. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2242. with
  2243. [
  2244. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  2245. ]
  2246. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  2247. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  2248. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/StreamGuard.h(139): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  2249. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2250. with
  2251. [
  2252. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  2253. ]
  2254. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2255. with
  2256. [
  2257. T=c10::impl::VirtualGuardImpl
  2258. ]
  2259. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2260. with
  2261. [
  2262. T=c10::impl::VirtualGuardImpl
  2263. ]
  2264. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2265. with
  2266. [
  2267. T=c10::impl::VirtualGuardImpl
  2268. ]
  2269. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::VirtualGuardImpl>' being compiled
  2270. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  2271. with
  2272. [
  2273. T=c10::impl::VirtualGuardImpl
  2274. ]
  2275. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/StreamGuard.h(162): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  2276. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2277. with
  2278. [
  2279. T=c10::impl::VirtualGuardImpl
  2280. ]
  2281. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2282. with
  2283. [
  2284. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  2285. ]
  2286. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2287. with
  2288. [
  2289. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  2290. ]
  2291. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2292. with
  2293. [
  2294. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  2295. ]
  2296. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>>' being compiled
  2297. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue_inl.h(853): note: see reference to class template instantiation 'c10::optional<std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>>' being compiled
  2298. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2299. with
  2300. [
  2301. T=std::vector<c10::ivalue::Future::WeakStorage,std::allocator<c10::ivalue::Future::WeakStorage>>
  2302. ]
  2303. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2304. with
  2305. [
  2306. T=torch::autograd::ViewInfo
  2307. ]
  2308. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2309. with
  2310. [
  2311. T=torch::autograd::ViewInfo
  2312. ]
  2313. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2314. with
  2315. [
  2316. T=torch::autograd::ViewInfo
  2317. ]
  2318. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::autograd::ViewInfo>' being compiled
  2319. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/variable.h(570): note: see reference to class template instantiation 'c10::optional<torch::autograd::ViewInfo>' being compiled
  2320. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2321. with
  2322. [
  2323. T=torch::autograd::ViewInfo
  2324. ]
  2325. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2326. with
  2327. [
  2328. T=c10::IValue
  2329. ]
  2330. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2331. with
  2332. [
  2333. T=c10::IValue
  2334. ]
  2335. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2336. with
  2337. [
  2338. T=c10::IValue
  2339. ]
  2340. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::IValue>' being compiled
  2341. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/function_schema.h(183): note: see reference to class template instantiation 'c10::optional<c10::IValue>' being compiled
  2342. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2343. with
  2344. [
  2345. T=c10::IValue
  2346. ]
  2347. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2348. with
  2349. [
  2350. T=c10::AliasInfo
  2351. ]
  2352. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2353. with
  2354. [
  2355. T=c10::AliasInfo
  2356. ]
  2357. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2358. with
  2359. [
  2360. T=c10::AliasInfo
  2361. ]
  2362. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::AliasInfo>' being compiled
  2363. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/function_schema.h(28): note: see reference to class template instantiation 'c10::optional<c10::AliasInfo>' being compiled
  2364. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2365. with
  2366. [
  2367. T=c10::AliasInfo
  2368. ]
  2369. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2370. with
  2371. [
  2372. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  2373. ]
  2374. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2375. with
  2376. [
  2377. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  2378. ]
  2379. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2380. with
  2381. [
  2382. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  2383. ]
  2384. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<T,std::allocator<T>>>' being compiled
  2385. with
  2386. [
  2387. T=c10::SymInt
  2388. ]
  2389. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/ivalue.h(83): note: see reference to class template instantiation 'c10::optional<std::vector<T,std::allocator<T>>>' being compiled
  2390. with
  2391. [
  2392. T=c10::SymInt
  2393. ]
  2394. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h(376): note: see reference to class template instantiation 'c10::OptionalArray<c10::SymInt>' being compiled
  2395. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/boxing/impl/make_boxed_from_unboxed_functor.h(386): note: see reference to class template instantiation 'c10::impl::ivalue_to_arg<c10::OptionalArray<c10::SymInt>,AllowDeprecatedTypes>' being compiled
  2396. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2397. with
  2398. [
  2399. T=std::vector<c10::SymInt,std::allocator<c10::SymInt>>
  2400. ]
  2401. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2402. with
  2403. [
  2404. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  2405. ]
  2406. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2407. with
  2408. [
  2409. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  2410. ]
  2411. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2412. with
  2413. [
  2414. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  2415. ]
  2416. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::either<c10::OperatorName,c10::FunctionSchema>>' being compiled
  2417. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/op_registration/op_registration.h(434): note: see reference to class template instantiation 'c10::optional<c10::either<c10::OperatorName,c10::FunctionSchema>>' being compiled
  2418. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2419. with
  2420. [
  2421. T=c10::either<c10::OperatorName,c10::FunctionSchema>
  2422. ]
  2423. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2424. with
  2425. [
  2426. T=at::StepCallbacks
  2427. ]
  2428. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2429. with
  2430. [
  2431. T=at::StepCallbacks
  2432. ]
  2433. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2434. with
  2435. [
  2436. T=at::StepCallbacks
  2437. ]
  2438. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::StepCallbacks>' being compiled
  2439. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/function.h(160): note: see reference to class template instantiation 'c10::optional<at::StepCallbacks>' being compiled
  2440. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2441. with
  2442. [
  2443. T=at::StepCallbacks
  2444. ]
  2445. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2446. with
  2447. [
  2448. T=c10::DimVector
  2449. ]
  2450. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2451. with
  2452. [
  2453. T=c10::DimVector
  2454. ]
  2455. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2456. with
  2457. [
  2458. T=c10::DimVector
  2459. ]
  2460. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::DimVector>' being compiled
  2461. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/TensorIterator.h(915): note: see reference to class template instantiation 'c10::optional<c10::DimVector>' being compiled
  2462. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2463. with
  2464. [
  2465. T=c10::DimVector
  2466. ]
  2467. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2468. with
  2469. [
  2470. T=c10::impl::AnnotatedSchema
  2471. ]
  2472. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2473. with
  2474. [
  2475. T=c10::impl::AnnotatedSchema
  2476. ]
  2477. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2478. with
  2479. [
  2480. T=c10::impl::AnnotatedSchema
  2481. ]
  2482. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::AnnotatedSchema>' being compiled
  2483. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/dispatch/OperatorEntry.h(223): note: see reference to class template instantiation 'c10::optional<c10::impl::AnnotatedSchema>' being compiled
  2484. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2485. with
  2486. [
  2487. T=c10::impl::AnnotatedSchema
  2488. ]
  2489. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2490. with
  2491. [
  2492. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  2493. ]
  2494. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2495. with
  2496. [
  2497. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  2498. ]
  2499. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2500. with
  2501. [
  2502. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  2503. ]
  2504. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::OperatorEntry::CppSignatureWithDebug>' being compiled
  2505. F:\Python 3.10.8\lib\site-packages\torch\include\ATen/core/dispatch/OperatorEntry.h(286): note: see reference to class template instantiation 'c10::optional<c10::impl::OperatorEntry::CppSignatureWithDebug>' being compiled
  2506. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2507. with
  2508. [
  2509. T=c10::impl::OperatorEntry::CppSignatureWithDebug
  2510. ]
  2511. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2512. with
  2513. [
  2514. T=std::tuple<std::string,size_t,size_t>
  2515. ]
  2516. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2517. with
  2518. [
  2519. T=std::tuple<std::string,size_t,size_t>
  2520. ]
  2521. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2522. with
  2523. [
  2524. T=std::tuple<std::string,size_t,size_t>
  2525. ]
  2526. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::tuple<std::string,size_t,size_t>>' being compiled
  2527. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/frontend/source_range.h(357): note: see reference to class template instantiation 'c10::optional<std::tuple<std::string,size_t,size_t>>' being compiled
  2528. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2529. with
  2530. [
  2531. T=std::tuple<std::string,size_t,size_t>
  2532. ]
  2533. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2534. with
  2535. [
  2536. T=torch::jit::SourceRange
  2537. ]
  2538. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2539. with
  2540. [
  2541. T=torch::jit::SourceRange
  2542. ]
  2543. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2544. with
  2545. [
  2546. T=torch::jit::SourceRange
  2547. ]
  2548. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::SourceRange>' being compiled
  2549. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/frontend/source_range.h(380): note: see reference to class template instantiation 'c10::optional<torch::jit::SourceRange>' being compiled
  2550. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2551. with
  2552. [
  2553. T=torch::jit::SourceRange
  2554. ]
  2555. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2556. with
  2557. [
  2558. T=torch::jit::InlinedCallStackPtr
  2559. ]
  2560. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2561. with
  2562. [
  2563. T=torch::jit::InlinedCallStackPtr
  2564. ]
  2565. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2566. with
  2567. [
  2568. T=torch::jit::InlinedCallStackPtr
  2569. ]
  2570. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::InlinedCallStackPtr>' being compiled
  2571. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/scope.h(127): note: see reference to class template instantiation 'c10::optional<torch::jit::InlinedCallStackPtr>' being compiled
  2572. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2573. with
  2574. [
  2575. T=torch::jit::InlinedCallStackPtr
  2576. ]
  2577. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2578. with
  2579. [
  2580. T=torch::jit::ModuleInstanceInfo
  2581. ]
  2582. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2583. with
  2584. [
  2585. T=torch::jit::ModuleInstanceInfo
  2586. ]
  2587. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2588. with
  2589. [
  2590. T=torch::jit::ModuleInstanceInfo
  2591. ]
  2592. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::ModuleInstanceInfo>' being compiled
  2593. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/scope.h(140): note: see reference to class template instantiation 'c10::optional<torch::jit::ModuleInstanceInfo>' being compiled
  2594. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2595. with
  2596. [
  2597. T=torch::jit::ModuleInstanceInfo
  2598. ]
  2599. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2600. with
  2601. [
  2602. T=torch::jit::ScopePtr
  2603. ]
  2604. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2605. with
  2606. [
  2607. T=torch::jit::ScopePtr
  2608. ]
  2609. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2610. with
  2611. [
  2612. T=torch::jit::ScopePtr
  2613. ]
  2614. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::ScopePtr>' being compiled
  2615. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/ir/constants.h(29): note: see reference to class template instantiation 'c10::optional<torch::jit::ScopePtr>' being compiled
  2616. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2617. with
  2618. [
  2619. T=torch::jit::ScopePtr
  2620. ]
  2621. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2622. with
  2623. [
  2624. T=at::ThreadLocalState
  2625. ]
  2626. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2627. with
  2628. [
  2629. T=at::ThreadLocalState
  2630. ]
  2631. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2632. with
  2633. [
  2634. T=at::ThreadLocalState
  2635. ]
  2636. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<at::ThreadLocalState>' being compiled
  2637. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/runtime/interpreter.h(150): note: see reference to class template instantiation 'c10::optional<at::ThreadLocalState>' being compiled
  2638. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2639. with
  2640. [
  2641. T=at::ThreadLocalState
  2642. ]
  2643. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2644. with
  2645. [
  2646. T=std::shared_ptr<torch::jit::Graph>
  2647. ]
  2648. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2649. with
  2650. [
  2651. T=std::shared_ptr<torch::jit::Graph>
  2652. ]
  2653. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2654. with
  2655. [
  2656. T=std::shared_ptr<torch::jit::Graph>
  2657. ]
  2658. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::shared_ptr<torch::jit::Graph>>' being compiled
  2659. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include\array(597): note: see reference to class template instantiation 'c10::optional<std::shared_ptr<torch::jit::Graph>>' being compiled
  2660. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/function_impl.h(165): note: see reference to class template instantiation 'std::array<c10::optional<std::shared_ptr<torch::jit::Graph>>,4>' being compiled
  2661. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2662. with
  2663. [
  2664. T=std::shared_ptr<torch::jit::Graph>
  2665. ]
  2666. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2667. with
  2668. [
  2669. T=torch::jit::GraphExecutor
  2670. ]
  2671. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2672. with
  2673. [
  2674. T=torch::jit::GraphExecutor
  2675. ]
  2676. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2677. with
  2678. [
  2679. T=torch::jit::GraphExecutor
  2680. ]
  2681. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::GraphExecutor>' being compiled
  2682. G:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include\array(597): note: see reference to class template instantiation 'c10::optional<torch::jit::GraphExecutor>' being compiled
  2683. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/function_impl.h(179): note: see reference to class template instantiation 'std::array<c10::optional<torch::jit::GraphExecutor>,4>' being compiled
  2684. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2685. with
  2686. [
  2687. T=torch::jit::GraphExecutor
  2688. ]
  2689. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2690. with
  2691. [
  2692. T=torch::jit::Method
  2693. ]
  2694. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2695. with
  2696. [
  2697. T=torch::jit::Method
  2698. ]
  2699. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2700. with
  2701. [
  2702. T=torch::jit::Method
  2703. ]
  2704. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::jit::Method>' being compiled
  2705. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/object.h(46): note: see reference to class template instantiation 'c10::optional<torch::jit::Method>' being compiled
  2706. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2707. with
  2708. [
  2709. T=torch::jit::Method
  2710. ]
  2711. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2712. with
  2713. [
  2714. T=std::vector<std::string,std::allocator<std::string>>
  2715. ]
  2716. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2717. with
  2718. [
  2719. T=std::vector<std::string,std::allocator<std::string>>
  2720. ]
  2721. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2722. with
  2723. [
  2724. T=std::vector<std::string,std::allocator<std::string>>
  2725. ]
  2726. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<std::string,std::allocator<std::string>>>' being compiled
  2727. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/jit/api/module.h(304): note: see reference to class template instantiation 'c10::optional<std::vector<std::string,std::allocator<std::string>>>' being compiled
  2728. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2729. with
  2730. [
  2731. T=std::vector<std::string,std::allocator<std::string>>
  2732. ]
  2733. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2734. with
  2735. [
  2736. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  2737. ]
  2738. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2739. with
  2740. [
  2741. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  2742. ]
  2743. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2744. with
  2745. [
  2746. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  2747. ]
  2748. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>' being compiled
  2749. F:\Python 3.10.8\lib\site-packages\torch\include\torch/csrc/autograd/profiler_legacy.h(410): note: see reference to class template instantiation 'c10::optional<std::function<void (const torch::autograd::profiler::thread_event_lists &)>>' being compiled
  2750. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2751. with
  2752. [
  2753. T=std::function<void (const torch::autograd::profiler::thread_event_lists &)>
  2754. ]
  2755. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2756. with
  2757. [
  2758. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  2759. ]
  2760. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2761. with
  2762. [
  2763. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  2764. ]
  2765. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2766. with
  2767. [
  2768. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  2769. ]
  2770. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>' being compiled
  2771. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/loss.h(453): note: see reference to class template instantiation 'c10::optional<torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t>' being compiled
  2772. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2773. with
  2774. [
  2775. T=torch::nn::TripletMarginWithDistanceLossOptions::distance_function_t
  2776. ]
  2777. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2778. with
  2779. [
  2780. T=std::vector<double,std::allocator<double>>
  2781. ]
  2782. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2783. with
  2784. [
  2785. T=std::vector<double,std::allocator<double>>
  2786. ]
  2787. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2788. with
  2789. [
  2790. T=std::vector<double,std::allocator<double>>
  2791. ]
  2792. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<T,std::allocator<T>>>' being compiled
  2793. with
  2794. [
  2795. T=double
  2796. ]
  2797. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/options/upsampling.h(27): note: see reference to class template instantiation 'c10::optional<std::vector<T,std::allocator<T>>>' being compiled
  2798. with
  2799. [
  2800. T=double
  2801. ]
  2802. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2803. with
  2804. [
  2805. T=std::vector<double,std::allocator<double>>
  2806. ]
  2807. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2808. with
  2809. [
  2810. T=std::tuple<at::Tensor,at::Tensor>
  2811. ]
  2812. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2813. with
  2814. [
  2815. T=std::tuple<at::Tensor,at::Tensor>
  2816. ]
  2817. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2818. with
  2819. [
  2820. T=std::tuple<at::Tensor,at::Tensor>
  2821. ]
  2822. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::tuple<at::Tensor,at::Tensor>>' being compiled
  2823. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/nn/modules/rnn.h(165): note: see reference to class template instantiation 'c10::optional<std::tuple<at::Tensor,at::Tensor>>' being compiled
  2824. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2825. with
  2826. [
  2827. T=std::tuple<at::Tensor,at::Tensor>
  2828. ]
  2829. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2830. with
  2831. [
  2832. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  2833. ]
  2834. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2835. with
  2836. [
  2837. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  2838. ]
  2839. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2840. with
  2841. [
  2842. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  2843. ]
  2844. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<std::vector<at::Tensor,std::allocator<at::Tensor>>>' being compiled
  2845. F:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include\torch/optim/lbfgs.h(50): note: see reference to class template instantiation 'c10::optional<std::vector<at::Tensor,std::allocator<at::Tensor>>>' being compiled
  2846. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2847. with
  2848. [
  2849. T=std::vector<at::Tensor,std::allocator<at::Tensor>>
  2850. ]
  2851. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2852. with
  2853. [
  2854. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  2855. ]
  2856. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2857. with
  2858. [
  2859. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  2860. ]
  2861. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2862. with
  2863. [
  2864. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  2865. ]
  2866. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  2867. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  2868. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(140): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  2869. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2870. with
  2871. [
  2872. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  2873. ]
  2874. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2875. with
  2876. [
  2877. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  2878. ]
  2879. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2880. with
  2881. [
  2882. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  2883. ]
  2884. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2885. with
  2886. [
  2887. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  2888. ]
  2889. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  2890. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  2891. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(273): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  2892. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2893. with
  2894. [
  2895. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  2896. ]
  2897. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  2898. with
  2899. [
  2900. T=c10::cuda::impl::CUDAGuardImpl
  2901. ]
  2902. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  2903. with
  2904. [
  2905. T=c10::cuda::impl::CUDAGuardImpl
  2906. ]
  2907. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  2908. with
  2909. [
  2910. T=c10::cuda::impl::CUDAGuardImpl
  2911. ]
  2912. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::cuda::impl::CUDAGuardImpl>' being compiled
  2913. F:\Python 3.10.8\lib\site-packages\torch\include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  2914. with
  2915. [
  2916. T=c10::cuda::impl::CUDAGuardImpl
  2917. ]
  2918. F:\Python 3.10.8\lib\site-packages\torch\include\c10/cuda/CUDAGuard.h(292): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  2919. F:\Python 3.10.8\lib\site-packages\torch\include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  2920. with
  2921. [
  2922. T=c10::cuda::impl::CUDAGuardImpl
  2923. ]
  2924. "C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\bin\nvcc" -c F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/src/fmha_block_dgrad_fp16_kernel_loop.sm80.cu -o build\temp.win-amd64-cpython-310\Release\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc/flash_attn/src/fmha_block_dgrad_fp16_kernel_loop.sm80.obj -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src -IF:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\cutlass\include "-IF:\Python 3.10.8\lib\site-packages\torch\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\torch\csrc\api\include" "-IF:\Python 3.10.8\lib\site-packages\torch\include\TH" "-IF:\Python 3.10.8\lib\site-packages\torch\include\THC" "-IC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7\include" "-IF:\Python 3.10.8\include" "-IF:\Python 3.10.8\Include" -IG:\Visual_studio\2019\VC\Tools\MSVC\14.29.30037\include "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.8\include\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\shared" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\um" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\winrt" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.19041.0\cppwinrt" -Xcudafe --diag_suppress=dll_interface_conflict_dllexport_assumed -Xcudafe --diag_suppress=dll_interface_conflict_none_assumed -Xcudafe --diag_suppress=field_without_dll_interface -Xcudafe --diag_suppress=base_class_has_different_dll_interface -Xcompiler /EHsc -Xcompiler /wd4190 -Xcompiler /wd4018 -Xcompiler /wd4275 -Xcompiler /wd4267 -Xcompiler /wd4244 -Xcompiler /wd4251 -Xcompiler /wd4819 -Xcompiler /MD -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -DHAS_PYTORCH --use_fast_math -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --extended-lambda --generate-line-info -DNDEBUG --threads 4 --ptxas-options=-v -std=c++17 -Xcompiler /Zc:lambda -Xcompiler /Zc:preprocessor -O3 --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -std=c++17 -gencode=arch=compute_75,code=sm_75 -gencode=arch=compute_80,code=sm_80 -gencode=arch=compute_86,code=sm_86 --generate-line-info -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=_C_flashattention -D_GLIBCXX_USE_CXX11_ABI=0 --use-local-env
  2925. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  2926. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  2927. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  2928. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  2929. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  2930. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  2931. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  2932. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  2933. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  2934. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  2935. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  2936. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  2937. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  2938. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_OPERATORS__' with '/U__CUDA_NO_HALF_OPERATORS__'
  2939. cl : Command line warning D9025 : overriding '/D__CUDA_NO_HALF_CONVERSIONS__' with '/U__CUDA_NO_HALF_CONVERSIONS__'
  2940. fmha_block_dgrad_fp16_kernel_loop.sm80.cu
  2941. F:/Python 3.10.8/lib/site-packages/torch/include\c10/macros/Macros.h(138): warning C4067: unexpected tokens following preprocessor directive - expected a newline
  2942. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  2943.  
  2944. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  2945. detected during:
  2946. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  2947. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  2948. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  2949. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  2950. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  2951. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  2952. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  2953. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  2954. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  2955. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  2956.  
  2957. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  2958. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  2959. (56): here
  2960.  
  2961. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  2962. detected during:
  2963. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  2964. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  2965. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  2966. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  2967. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  2968. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  2969. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  2970. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  2971. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  2972. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  2973.  
  2974. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  2975. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  2976. (59): here
  2977.  
  2978. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  2979. detected during:
  2980. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  2981. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  2982. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  2983. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  2984. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  2985. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  2986. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  2987. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  2988. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  2989. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  2990.  
  2991. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  2992. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  2993. (62): here
  2994.  
  2995. ptxas info : 25 bytes gmem
  2996. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  2997. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  2998. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  2999. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3000. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3001. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3002. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3003. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3004. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3005. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3006. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3007. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3008. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3009. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3010. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3011. ptxas info : Used 253 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3012. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3013. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3014. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3015. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3016. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3017. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3018. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3019. ptxas info : Used 251 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3020. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3021. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3022. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3023. ptxas info : Used 244 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3024. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3025. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3026. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3027. ptxas info : Used 240 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3028. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3029. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3030. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3031. ptxas info : Used 253 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3032. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3033. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3034. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3035. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3036. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3037. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3038. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3039. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3040. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3041. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3042. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3043. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3044. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3045. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3046. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3047. ptxas info : Used 239 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3048. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3049. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3050. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3051. ptxas info : Used 245 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3052. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3053. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3054. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3055. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3056. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3057. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3058. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3059. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3060. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3061. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3062. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3063. ptxas info : Used 221 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3064. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3065. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3066. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3067. ptxas info : Used 223 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3068. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3069. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3070. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3071. ptxas info : Used 235 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3072. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3073. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3074. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3075. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3076. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3077. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3078. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3079. ptxas info : Used 252 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3080. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3081. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3082. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3083. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3084. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3085. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3086. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3087. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3088. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3089. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3090. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3091. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3092. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3093. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3094. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3095. ptxas info : Used 194 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3096. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3097. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3098. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3099. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3100. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3101. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3102. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3103. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3104. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_86'
  3105. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3106. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3107. ptxas info : Used 228 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3108. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3109. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3110. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3111. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3112. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3113. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3114. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3115. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3116. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3117. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3118. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3119. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3120. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_86'
  3121. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3122. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3123. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3124. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3125. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3126. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3127. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3128. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3129. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3130. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3131. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3132. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3133. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3134. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3135. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3136. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_86'
  3137. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3138. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3139. ptxas info : Used 232 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3140. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  3141.  
  3142. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3143. detected during:
  3144. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3145. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3146. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3147. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3148. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3149. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3150. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3151. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3152. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  3153. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  3154.  
  3155. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3156. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  3157. (56): here
  3158.  
  3159. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3160. detected during:
  3161. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3162. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3163. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3164. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3165. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3166. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3167. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3168. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3169. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  3170. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  3171.  
  3172. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3173. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  3174. (59): here
  3175.  
  3176. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3177. detected during:
  3178. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3179. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3180. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3181. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3182. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3183. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3184. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3185. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3186. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  3187. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  3188.  
  3189. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3190. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  3191. (62): here
  3192.  
  3193. C:/Program Files (x86)/Windows Kits/10/include/10.0.19041.0/ucrt\fenv.h(113): warning #550-D: variable "_Ans" was set but never used
  3194.  
  3195. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3196. detected during:
  3197. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 16, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3198. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3199. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3200. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3201. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3202. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3203. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3204. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3205. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  3206. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(56): here
  3207.  
  3208. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3209. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 16, 16, 1, 8, 8U, __half>]"
  3210. (56): here
  3211.  
  3212. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3213. detected during:
  3214. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 32, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3215. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3216. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3217. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3218. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3219. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3220. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3221. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3222. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  3223. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(59): here
  3224.  
  3225. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3226. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 32, 16, 1, 8, 8U, __half>]"
  3227. (59): here
  3228.  
  3229. F:/Stable_Diffusion/stable-diffusion-webui-master/repositories/xformers/third_party/flash-attention/csrc/flash_attn/src\fmha/gmem_tile.h(469): warning #177-D: variable "warp" was declared but never referenced
  3230. detected during:
  3231. instantiation of "fmha::Gmem_summary_stats<Cta_tile>::Gmem_summary_stats(void *, const Params &, int) [with Cta_tile=fmha::Cta_tile_<16, 256, 64, 1, 8, 1>, Params=FMHA_dgrad_params]"
  3232. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(187): here
  3233. instantiation of "void fmha::compute_block_dq_dk_dv_1xN_one_iter<Kernel_traits,Is_dropout,Is_causal,Is_first,Is_last,Params,Prng>(const Params &, Prng &, int) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, Is_first=true, Is_last=true, Params=FMHA_dgrad_params, Prng=<unnamed>::Philox]"
  3234. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_kernel_1xN_loop.h(752): here
  3235. instantiation of "void fmha::compute_block_dq_dk_dv_1xN<Kernel_traits,Is_dropout,Is_causal,loop_steps,Params>(const Params &) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1, Params=FMHA_dgrad_params]"
  3236. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(9): here
  3237. instantiation of "void fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernel<Kernel_traits,Is_dropout,Is_causal,loop_steps>(FMHA_dgrad_params) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>, Is_dropout=true, Is_causal=true, loop_steps=-1]"
  3238. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(31): here
  3239. instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  3240. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(62): here
  3241.  
  3242. F:\Stable_Diffusion\stable-diffusion-webui-master\repositories\xformers\third_party\flash-attention\csrc\flash_attn\src\fmha_block_dgrad_fp16_kernel_loop.sm80.cu(14): warning #177-D: variable "smem_size_softmax" was declared but never referenced
  3243. detected during instantiation of "void run_fmha_block_dgrad_fp16_sm80_loop_<Kernel_traits>(const FMHA_dgrad_params &, cudaStream_t) [with Kernel_traits=FMHA_kernel_traits<256, 64, 16, 1, 8, 256U, __half>]"
  3244. (62): here
  3245.  
  3246. ptxas info : 25 bytes gmem
  3247. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3248. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3249. 8 bytes stack frame, 4 bytes spill stores, 4 bytes spill loads
  3250. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3251. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3252. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3253. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3254. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3255. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3256. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3257. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3258. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3259. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3260. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3261. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3262. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3263. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3264. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3265. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3266. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3267. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3268. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3269. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3270. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3271. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3272. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3273. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3274. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3275. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3276. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3277. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3278. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3279. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3280. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3281. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3282. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3283. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3284. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3285. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3286. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3287. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3288. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3289. 8 bytes stack frame, 4 bytes spill stores, 4 bytes spill loads
  3290. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3291. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3292. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3293. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3294. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3295. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3296. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3297. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3298. ptxas info : Used 239 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3299. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3300. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3301. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3302. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3303. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3304. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3305. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3306. ptxas info : Used 246 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3307. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3308. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3309. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3310. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3311. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3312. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3313. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3314. ptxas info : Used 221 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3315. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3316. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3317. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3318. ptxas info : Used 223 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3319. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3320. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3321. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3322. ptxas info : Used 235 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3323. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3324. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3325. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3326. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3327. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3328. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3329. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3330. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3331. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3332. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3333. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3334. ptxas info : Used 241 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3335. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3336. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3337. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3338. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3339. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3340. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3341. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3342. ptxas info : Used 250 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3343. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3344. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3345. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3346. ptxas info : Used 195 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3347. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3348. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3349. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3350. ptxas info : Used 209 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3351. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3352. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3353. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3354. ptxas info : Used 218 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3355. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_80'
  3356. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3357. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3358. ptxas info : Used 222 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3359. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3360. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3361. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3362. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3363. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3364. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3365. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3366. ptxas info : Used 160 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3367. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3368. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3369. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3370. ptxas info : Used 198 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3371. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_80'
  3372. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3373. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3374. ptxas info : Used 200 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3375. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3376. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3377. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3378. ptxas info : Used 209 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3379. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3380. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3381. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3382. ptxas info : Used 213 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3383. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3384. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3385. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3386. ptxas info : Used 226 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3387. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_80'
  3388. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3389. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3390. ptxas info : Used 233 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3391. ptxas info : 25 bytes gmem
  3392. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3393. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3394. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3395. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3396. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3397. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3398. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3399. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3400. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3401. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3402. 24 bytes stack frame, 28 bytes spill stores, 24 bytes spill loads
  3403. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3404. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3405. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3406. 32 bytes stack frame, 48 bytes spill stores, 36 bytes spill loads
  3407. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3408. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3409. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3410. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3411. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3412. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3413. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3414. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3415. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3416. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3417. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3418. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3419. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3420. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3421. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3422. 8 bytes stack frame, 8 bytes spill stores, 8 bytes spill loads
  3423. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3424. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3425. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3426. 32 bytes stack frame, 52 bytes spill stores, 36 bytes spill loads
  3427. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3428. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3429. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3430. 40 bytes stack frame, 44 bytes spill stores, 36 bytes spill loads
  3431. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3432. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3433. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3434. 32 bytes stack frame, 60 bytes spill stores, 56 bytes spill loads
  3435. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3436. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3437. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi64ELi16ELi1ELi8ELj256E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3438. 40 bytes stack frame, 84 bytes spill stores, 72 bytes spill loads
  3439. ptxas info : Used 255 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3440. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3441. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3442. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3443. ptxas info : Used 248 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3444. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3445. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3446. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3447. ptxas info : Used 245 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3448. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3449. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3450. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3451. ptxas info : Used 254 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3452. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3453. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3454. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3455. ptxas info : Used 249 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3456. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3457. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3458. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3459. ptxas info : Used 214 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3460. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3461. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3462. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3463. ptxas info : Used 216 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3464. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3465. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3466. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3467. ptxas info : Used 232 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3468. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3469. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3470. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3471. ptxas info : Used 224 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3472. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3473. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3474. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3475. ptxas info : Used 243 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3476. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3477. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3478. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3479. ptxas info : Used 249 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3480. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3481. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3482. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3483. ptxas info : Used 244 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3484. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3485. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi32ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3486. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3487. ptxas info : Used 251 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3488. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3489. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi2EEv17FMHA_dgrad_params
  3490. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3491. ptxas info : Used 204 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3492. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3493. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi2EEv17FMHA_dgrad_params
  3494. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3495. ptxas info : Used 218 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3496. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3497. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi2EEv17FMHA_dgrad_params
  3498. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3499. ptxas info : Used 220 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3500. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params' for 'sm_75'
  3501. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi2EEv17FMHA_dgrad_params
  3502. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3503. ptxas info : Used 236 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3504. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3505. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELi1EEv17FMHA_dgrad_params
  3506. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3507. ptxas info : Used 170 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3508. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3509. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELi1EEv17FMHA_dgrad_params
  3510. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3511. ptxas info : Used 186 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3512. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3513. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELi1EEv17FMHA_dgrad_params
  3514. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3515. ptxas info : Used 202 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3516. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params' for 'sm_75'
  3517. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELi1EEv17FMHA_dgrad_params
  3518. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3519. ptxas info : Used 208 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3520. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3521. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb0ELin1EEv17FMHA_dgrad_params
  3522. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3523. ptxas info : Used 216 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3524. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3525. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb0ELb1ELin1EEv17FMHA_dgrad_params
  3526. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3527. ptxas info : Used 220 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3528. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3529. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb0ELin1EEv17FMHA_dgrad_params
  3530. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3531. ptxas info : Used 229 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3532. ptxas info : Compiling entry function '_Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params' for 'sm_75'
  3533. ptxas info : Function properties for _Z47fmha_block_dgrad_fp16_sm80_dq_dk_dv_loop_kernelI18FMHA_kernel_traitsILi256ELi16ELi16ELi1ELi8ELj8E6__halfELb1ELb1ELin1EEv17FMHA_dgrad_params
  3534. 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
  3535. ptxas info : Used 237 registers, 632 bytes cmem[0], 16 bytes cmem[2]
  3536. tmpxft_00001a64_00000000-7_fmha_block_dgrad_fp16_kernel_loop.sm80.compute_86.cudafe1.cpp
  3537. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3538. with
  3539. [
  3540. T=c10::SymInt
  3541. ]
  3542. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3543. with
  3544. [
  3545. T=c10::SymInt
  3546. ]
  3547. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3548. with
  3549. [
  3550. T=c10::SymInt
  3551. ]
  3552. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::SymInt>' being compiled
  3553. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/TensorImpl.h(1577): note: see reference to class template instantiation 'c10::optional<c10::SymInt>' being compiled
  3554. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3555. with
  3556. [
  3557. T=c10::SymInt
  3558. ]
  3559. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/TensorImpl.h(2687): warning C4805: '|': unsafe mix of type 'uintptr_t' and type 'bool' in operation
  3560. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3561. with
  3562. [
  3563. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  3564. ]
  3565. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3566. with
  3567. [
  3568. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  3569. ]
  3570. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3571. with
  3572. [
  3573. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  3574. ]
  3575. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  3576. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>>' being compiled
  3577. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/DeviceGuard.h(178): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::impl::VirtualGuardImpl>' being compiled
  3578. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3579. with
  3580. [
  3581. T=c10::impl::InlineDeviceGuard<c10::impl::VirtualGuardImpl>
  3582. ]
  3583. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3584. with
  3585. [
  3586. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  3587. ]
  3588. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3589. with
  3590. [
  3591. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  3592. ]
  3593. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3594. with
  3595. [
  3596. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  3597. ]
  3598. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  3599. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineDeviceGuard.h(427): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  3600. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(140): note: see reference to class template instantiation 'c10::impl::InlineOptionalDeviceGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  3601. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3602. with
  3603. [
  3604. T=c10::impl::InlineDeviceGuard<c10::cuda::impl::CUDAGuardImpl>
  3605. ]
  3606. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3607. with
  3608. [
  3609. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  3610. ]
  3611. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3612. with
  3613. [
  3614. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  3615. ]
  3616. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3617. with
  3618. [
  3619. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  3620. ]
  3621. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  3622. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>>' being compiled
  3623. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(273): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  3624. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3625. with
  3626. [
  3627. T=c10::impl::InlineStreamGuard<c10::cuda::impl::CUDAGuardImpl>
  3628. ]
  3629. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3630. with
  3631. [
  3632. T=c10::cuda::impl::CUDAGuardImpl
  3633. ]
  3634. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3635. with
  3636. [
  3637. T=c10::cuda::impl::CUDAGuardImpl
  3638. ]
  3639. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3640. with
  3641. [
  3642. T=c10::cuda::impl::CUDAGuardImpl
  3643. ]
  3644. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::cuda::impl::CUDAGuardImpl>' being compiled
  3645. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  3646. with
  3647. [
  3648. T=c10::cuda::impl::CUDAGuardImpl
  3649. ]
  3650. F:/Python 3.10.8/lib/site-packages/torch/include\c10/cuda/CUDAGuard.h(292): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::cuda::impl::CUDAGuardImpl>' being compiled
  3651. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3652. with
  3653. [
  3654. T=c10::cuda::impl::CUDAGuardImpl
  3655. ]
  3656. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3657. with
  3658. [
  3659. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  3660. ]
  3661. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3662. with
  3663. [
  3664. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  3665. ]
  3666. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3667. with
  3668. [
  3669. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  3670. ]
  3671. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  3672. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(197): note: see reference to class template instantiation 'c10::optional<c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>>' being compiled
  3673. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/StreamGuard.h(139): note: see reference to class template instantiation 'c10::impl::InlineOptionalStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  3674. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3675. with
  3676. [
  3677. T=c10::impl::InlineStreamGuard<c10::impl::VirtualGuardImpl>
  3678. ]
  3679. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(212): warning C4624: 'c10::constexpr_storage_t<T>': destructor was implicitly defined as deleted
  3680. with
  3681. [
  3682. T=c10::impl::VirtualGuardImpl
  3683. ]
  3684. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(411): note: see reference to class template instantiation 'c10::constexpr_storage_t<T>' being compiled
  3685. with
  3686. [
  3687. T=c10::impl::VirtualGuardImpl
  3688. ]
  3689. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to class template instantiation 'c10::trivially_copyable_optimization_optional_base<T>' being compiled
  3690. with
  3691. [
  3692. T=c10::impl::VirtualGuardImpl
  3693. ]
  3694. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(554): note: see reference to alias template instantiation 'c10::OptionalBase<c10::impl::VirtualGuardImpl>' being compiled
  3695. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/impl/InlineStreamGuard.h(232): note: see reference to class template instantiation 'c10::optional<T>' being compiled
  3696. with
  3697. [
  3698. T=c10::impl::VirtualGuardImpl
  3699. ]
  3700. F:/Python 3.10.8/lib/site-packages/torch/include\c10/core/StreamGuard.h(162): note: see reference to class template instantiation 'c10::impl::InlineMultiStreamGuard<c10::impl::VirtualGuardImpl>' being compiled
  3701. F:/Python 3.10.8/lib/site-packages/torch/include\c10/util/Optional.h(446): warning C4624: 'c10::trivially_copyable_optimization_optional_base<T>': destructor was implicitly defined as deleted
  3702. with
  3703. [
  3704. T=c10::impl::VirtualGuardImpl
  3705. ]
  3706. C:\Users\User\AppData\Local\Temp\tmpxft_00001a64_00000000-7_fmha_block_dgrad_fp16_kernel_loop.sm80.compute_86.cudafe1.cpp : fatal error C1083: Cannot open compiler generated file: '': Invalid argument
  3707. error: command 'C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin\\nvcc.exe' failed with exit code 4294967295
  3708. [end of output]
  3709.  
  3710. note: This error originates from a subprocess, and is likely not a problem with pip.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!