API tools faq
paste
Guest User

more logs

a guest
May 2nd, 2026
14
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 19.02 KB | None | 0 0
raw download clone embed print report
  1. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299]
  2.  
  3. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299] █ █ █▄ ▄█
  4.  
  5. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299] ▄▄ ▄█ █ █ █ ▀▄▀ █ version 0.19.0
  6.  
  7. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299] █▄█▀ █ █ █ █ model H:\qwen3.6-windows-server\models\Qwen3.6-27B-int4-AutoRound
  8.  
  9. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299] ▀▀ ▀▀▀▀▀ ▀▀▀▀▀ ▀ ▀
  10.  
  11. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:299]
  12. (APIServer pid=5356) INFO 05-02 22:27:08 [utils.py:233] non-default args: {'model_tag': 'H:\\qwen3.6-windows-server\\models\\Qwen3.6-27B-int4-AutoRound', 'chat_template': 'H:\\qwen3.6-windows-server\\templates\\qwen3.5-enhanced.jinja', 'default_chat_template_kwargs': {'preserve_thinking': False}, 'enable_auto_tool_choice': True, 'tool_call_parser': 'qwen3_coder', 'host': '0.0.0.0', 'port': 5001, 'model': 'H:\\qwen3.6-windows-server\\models\\Qwen3.6-27B-int4-AutoRound', 'trust_remote_code': True, 'max_model_len': 120000, 'quantization': 'auto-round', 'served_model_name': ['qwen3.6-27b-autoround'], 'use_tqdm_on_load': False, 'attention_backend': 'TRITON_ATTN', 'reasoning_parser': 'qwen3', 'block_size': 32, 'gpu_memory_utilization': 0.948, 'kv_cache_dtype': 'fp8_e4m3', 'enable_prefix_caching': True, 'limit_mm_per_prompt': {'image': 0, 'video': 0}, 'max_num_batched_tokens': 4128, 'max_num_seqs': 1, 'enable_chunked_prefill': True, 'speculative_config': {'method': 'mtp', 'num_speculative_tokens': 4}}
  13. (APIServer pid=5356) INFO 05-02 22:27:08 [system_utils.py:279] Windows detected, skipping ulimit adjustment.
  14. (APIServer pid=5356) WARNING 05-02 22:27:08 [envs.py:1786] Unknown vLLM environment variable detected: VLLM_ATTENTION_BACKEND
  15. (APIServer pid=5356) WARNING 05-02 22:27:08 [envs.py:1786] Unknown vLLM environment variable detected: VLLM_MODEL_DIR
  16. (APIServer pid=5356) WARNING 05-02 22:27:08 [envs.py:1786] Unknown vLLM environment variable detected: VLLM_SLEEP_WHEN_IDLE
  17. (APIServer pid=5356) INFO 05-02 22:27:08 [model.py:554] Resolved architecture: Qwen3_5ForConditionalGeneration
  18. (APIServer pid=5356) INFO 05-02 22:27:08 [model.py:1685] Using max model len 120000
  19. (APIServer pid=5356) INFO 05-02 22:27:09 [cache.py:253] Using fp8_e4m3 data type to store kv cache. It reduces the GPU memory footprint and boosts the performance. Meanwhile, it may cause accuracy drop without a proper scaling factor
  20. (APIServer pid=5356) INFO 05-02 22:27:09 [model.py:554] Resolved architecture: Qwen3_5MTP
  21. (APIServer pid=5356) INFO 05-02 22:27:09 [model.py:1685] Using max model len 262144
  22. (APIServer pid=5356) WARNING 05-02 22:27:09 [speculative.py:521] Enabling num_speculative_tokens > 1 will run multiple times of forward on same MTP layer,which may result in lower acceptance rate
  23. (APIServer pid=5356) INFO 05-02 22:27:09 [scheduler.py:238] Chunked prefill is enabled with max_num_batched_tokens=4128.
  24. (APIServer pid=5356) WARNING 05-02 22:27:09 [config.py:306] Mamba cache mode is set to 'align' for Qwen3_5ForConditionalGeneration by default when prefix caching is enabled
  25. (APIServer pid=5356) INFO 05-02 22:27:09 [config.py:326] Warning: Prefix caching in Mamba cache 'align' mode is currently enabled. Its support for Mamba layers is experimental. Please report any issues you may observe.
  26. (APIServer pid=5356) INFO 05-02 22:27:09 [vllm.py:799] Asynchronous scheduling is enabled.
  27. (APIServer pid=5356) INFO 05-02 22:27:09 [kernel.py:199] Final IR op priority after setting platform defaults: IrOpPriorityConfig(rms_norm=['native'])
  28. (APIServer pid=5356) WARNING 05-02 22:27:09 [vllm.py:1362] max_num_scheduled_tokens is set to 4128 based on the speculative decoding settings. This may lead to suboptimal performance. Consider increasing max_num_batched_tokens to accommodate the additional draft token slots, or decrease num_speculative_tokens or max_num_seqs.
  29. (APIServer pid=5356) INFO 05-02 22:27:10 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
  30. (EngineCore pid=25592) INFO 05-02 22:27:19 [core.py:105] Initializing a V1 LLM engine (v0.19.0) with config: model='H:\\qwen3.6-windows-server\\models\\Qwen3.6-27B-int4-AutoRound', speculative_config=SpeculativeConfig(method='mtp', model='H:\\qwen3.6-windows-server\\models\\Qwen3.6-27B-int4-AutoRound', num_spec_tokens=4), tokenizer='H:\\qwen3.6-windows-server\\models\\Qwen3.6-27B-int4-AutoRound', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=120000, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1, data_parallel_size=1, decode_context_parallel_size=1, dcp_comm_backend=ag_rs, disable_custom_all_reduce=False, quantization=inc, quantization_config=None, enforce_eager=False, enable_return_routed_experts=False, kv_cache_dtype=fp8_e4m3, device_config=cuda, structured_outputs_config=StructuredOutputsConfig(backend='auto', disable_any_whitespace=False, disable_additional_properties=False, reasoning_parser='qwen3', reasoning_parser_plugin='', enable_in_reasoning=False), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, kv_cache_metrics=False, kv_cache_metrics_sample=0.01, cudagraph_metrics=False, enable_layerwise_nvtx_tracing=False, enable_mfu_metrics=False, enable_mm_processor_stats=False, enable_logging_iteration_details=False), seed=0, served_model_name=qwen3.6-27b-autoround, enable_prefix_caching=True, enable_chunked_prefill=True, pooler_config=None, compilation_config={'mode': <CompilationMode.VLLM_COMPILE: 3>, 'debug_dump_path': None, 'cache_dir': '', 'compile_cache_save_format': 'binary', 'backend': 'inductor', 'custom_ops': ['none'], 'ir_enable_torch_wrap': True, 'splitting_ops': ['vllm::unified_attention', 'vllm::unified_attention_with_output', 'vllm::unified_mla_attention', 'vllm::unified_mla_attention_with_output', 'vllm::mamba_mixer2', 'vllm::mamba_mixer', 'vllm::short_conv', 'vllm::linear_attention', 'vllm::plamo2_mamba_mixer', 'vllm::gdn_attention_core', 'vllm::olmo_hybrid_gdn_full_forward', 'vllm::kda_attention', 'vllm::sparse_attn_indexer', 'vllm::rocm_aiter_sparse_attn_indexer', 'vllm::unified_kv_cache_update', 'vllm::unified_mla_kv_cache_update'], 'compile_mm_encoder': False, 'cudagraph_mm_encoder': False, 'encoder_cudagraph_token_budgets': [], 'encoder_cudagraph_max_images_per_batch': 0, 'compile_sizes': [], 'compile_ranges_endpoints': [4128], 'inductor_compile_config': {'enable_auto_functionalized_v2': False, 'size_asserts': False, 'alignment_asserts': False, 'scalar_asserts': False, 'combo_kernels': True, 'benchmark_combo_kernel': True}, 'inductor_passes': {}, 'cudagraph_mode': <CUDAGraphMode.FULL_AND_PIECEWISE: (2, 1)>, 'cudagraph_num_of_warmups': 1, 'cudagraph_capture_sizes': [1, 2, 4, 8], 'cudagraph_copy_inputs': False, 'cudagraph_specialize_lora': True, 'use_inductor_graph_partition': False, 'pass_config': {'fuse_norm_quant': False, 'fuse_act_quant': False, 'fuse_attn_quant': False, 'enable_sp': False, 'fuse_gemm_comms': False, 'fuse_allreduce_rms': False}, 'max_cudagraph_capture_size': 8, 'dynamic_shapes_config': {'type': <DynamicShapesType.BACKED: 'backed'>, 'evaluate_guards': False, 'assume_32_bit_indexing': False}, 'local_cache_dir': None, 'fast_moe_cold_start': False, 'static_all_moe_layers': []}, kernel_config=KernelConfig(ir_op_priority=IrOpPriorityConfig(rms_norm=['native']), enable_flashinfer_autotune=True, moe_backend='auto')
  31. (EngineCore pid=25592) INFO 05-02 22:27:20 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
  32. (EngineCore pid=25592) INFO 05-02 22:27:20 [parallel_state.py:1455] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://172.19.0.1:55065 backend=gloo
  33. [W502 22:27:20.000000000 socket.cpp:764] [c10d] The client socket has failed to connect to [Shush]:55065 (system error: 10049 - .).
  34. [W502 22:27:20.000000000 socket.cpp:764] [c10d] The client socket has failed to connect to [Shush]:55065 (system error: 10049 - .).
  35. (EngineCore pid=25592) INFO 05-02 22:27:21 [parallel_state.py:1767] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A
  36. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] EngineCore failed to start.
  37.  
  38. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] Traceback (most recent call last):
  39.  
  40. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1082, in run_engine_core
  41.  
  42. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
  43.  
  44. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  45.  
  46. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  47.  
  48. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] return func(*args, **kwargs)
  49.  
  50. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
  51.  
  52. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 848, in __init__
  53.  
  54. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] super().__init__(
  55.  
  56. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 114, in __init__
  57.  
  58. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.model_executor = executor_class(vllm_config)
  59.  
  60. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  61.  
  62. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  63.  
  64. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] return func(*args, **kwargs)
  65.  
  66. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
  67.  
  68. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\abstract.py", line 109, in __init__
  69.  
  70. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self._init_executor()
  71.  
  72. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\uniproc_executor.py", line 47, in _init_executor
  73.  
  74. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.driver_worker.init_device()
  75.  
  76. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\worker_base.py", line 312, in init_device
  77.  
  78. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.worker.init_device() # type: ignore
  79.  
  80. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^
  81.  
  82. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  83.  
  84. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] return func(*args, **kwargs)
  85.  
  86. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
  87.  
  88. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_worker.py", line 311, in init_device
  89.  
  90. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.model_runner = GPUModelRunnerV1(self.vllm_config, self.device)
  91.  
  92. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  93.  
  94. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_model_runner.py", line 480, in __init__
  95.  
  96. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.sampler = Sampler(logprobs_mode=self.model_config.logprobs_mode)
  97.  
  98. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  99.  
  100. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\sampler.py", line 64, in __init__
  101.  
  102. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] self.topk_topp_sampler = TopKTopPSampler(logprobs_mode)
  103.  
  104. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  105.  
  106. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\ops\topk_topp_sampler.py", line 40, in __init__
  107.  
  108. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] from vllm.v1.attention.backends.flashinfer import FlashInferBackend
  109.  
  110. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\attention\backends\flashinfer.py", line 11, in <module>
  111.  
  112. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] from flashinfer import (
  113.  
  114. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\__init__.py", line 24, in <module>
  115.  
  116. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] from . import jit as jit
  117.  
  118. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] File "H:\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\jit\__init__.py", line 125, in <module>
  119.  
  120. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] raise ValueError(
  121.  
  122. (EngineCore pid=25592) ERROR 05-02 22:27:21 [core.py:1108] ValueError: CUDA_LIB_PATH is not set. CUDA_LIB_PATH need to be set with the absolute path to CUDA root folder on Windows (for example, set CUDA_LIB_PATH=C:\CUDA\v12.4)
  123. (EngineCore pid=25592) Process EngineCore:
  124. (EngineCore pid=25592) Traceback (most recent call last):
  125. (EngineCore pid=25592) File "multiprocessing\process.py", line 314, in _bootstrap
  126. (EngineCore pid=25592) File "multiprocessing\process.py", line 108, in run
  127. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1112, in run_engine_core
  128. (EngineCore pid=25592) raise e
  129. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1082, in run_engine_core
  130. (EngineCore pid=25592) engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
  131. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  132. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  133. (EngineCore pid=25592) return func(*args, **kwargs)
  134. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^
  135. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 848, in __init__
  136. (EngineCore pid=25592) super().__init__(
  137. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 114, in __init__
  138. (EngineCore pid=25592) self.model_executor = executor_class(vllm_config)
  139. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  140. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  141. (EngineCore pid=25592) return func(*args, **kwargs)
  142. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^
  143. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\abstract.py", line 109, in __init__
  144. (EngineCore pid=25592) self._init_executor()
  145. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\uniproc_executor.py", line 47, in _init_executor
  146. (EngineCore pid=25592) self.driver_worker.init_device()
  147. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\worker_base.py", line 312, in init_device
  148. (EngineCore pid=25592) self.worker.init_device() # type: ignore
  149. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^
  150. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
  151. (EngineCore pid=25592) return func(*args, **kwargs)
  152. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^
  153. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_worker.py", line 311, in init_device
  154. (EngineCore pid=25592) self.model_runner = GPUModelRunnerV1(self.vllm_config, self.device)
  155. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  156. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_model_runner.py", line 480, in __init__
  157. (EngineCore pid=25592) self.sampler = Sampler(logprobs_mode=self.model_config.logprobs_mode)
  158. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  159. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\sampler.py", line 64, in __init__
  160. (EngineCore pid=25592) self.topk_topp_sampler = TopKTopPSampler(logprobs_mode)
  161. (EngineCore pid=25592) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  162. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\ops\topk_topp_sampler.py", line 40, in __init__
  163. (EngineCore pid=25592) from vllm.v1.attention.backends.flashinfer import FlashInferBackend
  164. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\attention\backends\flashinfer.py", line 11, in <module>
  165. (EngineCore pid=25592) from flashinfer import (
  166. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\__init__.py", line 24, in <module>
  167. (EngineCore pid=25592) from . import jit as jit
  168. (EngineCore pid=25592) File "H:\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\jit\__init__.py", line 125, in <module>
  169. (EngineCore pid=25592) raise ValueError(
  170. (EngineCore pid=25592) ValueError: CUDA_LIB_PATH is not set. CUDA_LIB_PATH need to be set with the absolute path to CUDA root folder on Windows (for example, set CUDA_LIB_PATH=C:\CUDA\v12.4)
  171. forrtl: error (200): program aborting due to window-CLOSE event
  172. Image PC Routine Line Source
  173. KERNELBASE.dll 00007FFDD586A3CD Unknown Unknown Unknown
  174. KERNEL32.DLL 00007FFDD794E8D7 Unknown Unknown Unknown
  175. ntdll.dll 00007FFDD828C3FC Unknown Unknown Unknown
  176.  
Add Comment
Please, Sign In to add comment
Public Pastes
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!