Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- 2025-11-20T09:53:46.423838-07:00 granite systemd[1]: Stopping ollama.service - Ollama Service...
- 2025-11-20T09:53:46.430142-07:00 granite systemd[1]: ollama.service: Deactivated successfully.
- 2025-11-20T09:53:46.430508-07:00 granite systemd[1]: Stopped ollama.service - Ollama Service.
- 2025-11-20T09:53:46.430593-07:00 granite systemd[1]: ollama.service: Consumed 6.334s CPU time.
- 2025-11-20T09:53:46.461303-07:00 granite systemd[1]: Started ollama.service - Ollama Service.
- 2025-11-20T09:53:46.482207-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.481-07:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
- 2025-11-20T09:53:46.485156-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.485-07:00 level=INFO source=images.go:522 msg="total blobs: 54"
- 2025-11-20T09:53:46.485673-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.485-07:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
- 2025-11-20T09:53:46.485992-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.485-07:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)"
- 2025-11-20T09:53:46.486118-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
- 2025-11-20T09:53:46.486300-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
- 2025-11-20T09:53:46.486406-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=DEBUG source=gpu.go:74 msg="unrecognized L4T version" nv_tegra_release="# R38 (release), REVISION: 2.2, GCID: 42205042, BOARD: generic, EABI: aarch64, DATE: Thu Sep 25 22:47:11 UTC 2025\n# KERNEL_VARIANT: oot\nTARGET_USERSPACE_LIB_DIR=nvidia\nTARGET_USERSPACE_LIB_DIR_PATH=usr/lib/aarch64-linux-gnu/nvidia\nINSTALL_TYPE=\n"
- 2025-11-20T09:53:46.486466-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extraEnvs=map[]
- 2025-11-20T09:53:46.486889-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33799"
- 2025-11-20T09:53:46.486918-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.486-07:00 level=DEBUG source=server.go:393 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:46.498996-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.498-07:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
- 2025-11-20T09:53:46.502021-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.501-07:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:33799"
- 2025-11-20T09:53:46.508678-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
- 2025-11-20T09:53:46.508705-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
- 2025-11-20T09:53:46.508730-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:46.508824-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:46.508840-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
- 2025-11-20T09:53:46.508867-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
- 2025-11-20T09:53:46.508896-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
- 2025-11-20T09:53:46.508916-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
- 2025-11-20T09:53:46.508940-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.508-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
- 2025-11-20T09:53:46.514888-07:00 granite ollama[32079]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu.so
- 2025-11-20T09:53:46.515003-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.514-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:46.771207-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
- 2025-11-20T09:53:46.771250-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
- 2025-11-20T09:53:46.771288-07:00 granite ollama[32079]: ggml_cuda_init: found 1 CUDA devices:
- 2025-11-20T09:53:46.784287-07:00 granite ollama[32079]: Device 0: NVIDIA Thor, compute capability 11.0, VMM: yes, ID: GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600
- 2025-11-20T09:53:46.793915-07:00 granite ollama[32079]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
- 2025-11-20T09:53:46.793982-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.793-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
- 2025-11-20T09:53:46.794020-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.793-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:46.794078-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
- 2025-11-20T09:53:46.794107-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
- 2025-11-20T09:53:46.794156-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
- 2025-11-20T09:53:46.794184-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
- 2025-11-20T09:53:46.794214-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
- 2025-11-20T09:53:46.794243-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
- 2025-11-20T09:53:46.794272-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
- 2025-11-20T09:53:46.794307-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
- 2025-11-20T09:53:46.794336-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
- 2025-11-20T09:53:46.794365-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
- 2025-11-20T09:53:46.794397-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
- 2025-11-20T09:53:46.794440-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
- 2025-11-20T09:53:46.794481-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:46.794510-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
- 2025-11-20T09:53:46.794539-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
- 2025-11-20T09:53:46.794568-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
- 2025-11-20T09:53:46.794601-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
- 2025-11-20T09:53:46.794629-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
- 2025-11-20T09:53:46.794658-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
- 2025-11-20T09:53:46.794687-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
- 2025-11-20T09:53:46.794720-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
- 2025-11-20T09:53:46.794754-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.794-07:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=285.783796ms
- 2025-11-20T09:53:46.807341-07:00 granite ollama[32079]: ggml_nvml_get_device_memory NVML not supported for memory query, using system memory (total=131882475520, available=98828587008)
- 2025-11-20T09:53:46.807374-07:00 granite ollama[32079]: ggml_backend_cuda_device_get_memory device GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 utilizing NVML memory reporting free: 98828587008 total: 131882475520
- 2025-11-20T09:53:46.811225-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.811-07:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=16.868743ms
- 2025-11-20T09:53:46.811780-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.811-07:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" devices="[{DeviceID:{ID:GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 Library:CUDA} Name:CUDA0 Description:NVIDIA Thor FilterID: Integrated:true PCIID:0000:01:00.0 TotalMemory:131882475520 FreeMemory:98828587008 ComputeMajor:11 ComputeMinor:0 DriverMajor:13 DriverMinor:0 LibraryPath:[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]}]"
- 2025-11-20T09:53:46.811920-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.811-07:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=325.366826ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[]
- 2025-11-20T09:53:46.811960-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.811-07:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extraEnvs=map[]
- 2025-11-20T09:53:46.812268-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.812-07:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 37809"
- 2025-11-20T09:53:46.812305-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.812-07:00 level=DEBUG source=server.go:393 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13
- 2025-11-20T09:53:46.826923-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.826-07:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
- 2025-11-20T09:53:46.831606-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.831-07:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:37809"
- 2025-11-20T09:53:46.833193-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
- 2025-11-20T09:53:46.833216-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
- 2025-11-20T09:53:46.833245-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:46.833330-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:46.833346-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
- 2025-11-20T09:53:46.833380-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
- 2025-11-20T09:53:46.833402-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
- 2025-11-20T09:53:46.833423-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
- 2025-11-20T09:53:46.833449-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.833-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
- 2025-11-20T09:53:46.839800-07:00 granite ollama[32079]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu.so
- 2025-11-20T09:53:46.839915-07:00 granite ollama[32079]: time=2025-11-20T09:53:46.839-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v13
- 2025-11-20T09:53:47.071335-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
- 2025-11-20T09:53:47.071374-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
- 2025-11-20T09:53:47.071395-07:00 granite ollama[32079]: ggml_cuda_init: found 1 CUDA devices:
- 2025-11-20T09:53:47.071417-07:00 granite ollama[32079]: Device 0: NVIDIA Thor, compute capability 11.0, VMM: yes, ID: GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600
- 2025-11-20T09:53:47.071441-07:00 granite ollama[32079]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v13/libggml-cuda.so
- 2025-11-20T09:53:47.071562-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
- 2025-11-20T09:53:47.071601-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:47.071656-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
- 2025-11-20T09:53:47.071694-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
- 2025-11-20T09:53:47.071746-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
- 2025-11-20T09:53:47.071776-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
- 2025-11-20T09:53:47.071806-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
- 2025-11-20T09:53:47.071835-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
- 2025-11-20T09:53:47.071864-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
- 2025-11-20T09:53:47.071903-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
- 2025-11-20T09:53:47.071932-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
- 2025-11-20T09:53:47.071960-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
- 2025-11-20T09:53:47.071989-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
- 2025-11-20T09:53:47.072032-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
- 2025-11-20T09:53:47.072089-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:47.072115-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
- 2025-11-20T09:53:47.072143-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
- 2025-11-20T09:53:47.072173-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
- 2025-11-20T09:53:47.072197-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
- 2025-11-20T09:53:47.072226-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
- 2025-11-20T09:53:47.072254-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
- 2025-11-20T09:53:47.072283-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
- 2025-11-20T09:53:47.072311-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
- 2025-11-20T09:53:47.072339-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.071-07:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=238.838647ms
- 2025-11-20T09:53:47.083332-07:00 granite ollama[32079]: ggml_nvml_get_device_memory NVML not supported for memory query, using system memory (total=131882475520, available=98825433088)
- 2025-11-20T09:53:47.083376-07:00 granite ollama[32079]: ggml_backend_cuda_device_get_memory device GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 utilizing NVML memory reporting free: 98825433088 total: 131882475520
- 2025-11-20T09:53:47.087151-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=15.203135ms
- 2025-11-20T09:53:47.087549-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" devices="[{DeviceID:{ID:GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 Library:CUDA} Name:CUDA0 Description:NVIDIA Thor FilterID: Integrated:true PCIID:0000:01:00.0 TotalMemory:131882475520 FreeMemory:98825433088 ComputeMajor:11 ComputeMinor:0 DriverMajor:13 DriverMinor:0 LibraryPath:[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]}]"
- 2025-11-20T09:53:47.087638-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=275.640221ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extra_envs=map[]
- 2025-11-20T09:53:47.087667-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=DEBUG source=runner.go:120 msg="evaluating which, if any, devices to filter out" initial_count=2
- 2025-11-20T09:53:47.087695-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=TRACE source=runner.go:160 msg="supported GPU library combinations before filtering" supported=map[]
- 2025-11-20T09:53:47.087731-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=601.523103ms
- 2025-11-20T09:53:47.087763-07:00 granite ollama[32079]: time=2025-11-20T09:53:47.087-07:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 filter_id="" library=CUDA compute=11.0 name=CUDA0 description="NVIDIA Thor" libdirs=ollama,cuda_v12 driver=13.0 pci_id=0000:01:00.0 type=iGPU total="122.8 GiB" available="92.0 GiB"
- 2025-11-20T09:53:49.528631-07:00 granite avahi-daemon[975]: avahi_normalize_name() failed.
- 2025-11-20T09:53:49.528756-07:00 granite avahi-daemon[975]: avahi_key_new() failed.
- 2025-11-20T09:53:51.713794-07:00 granite ollama[32079]: [GIN] 2025/11/20 - 09:53:51 | 200 | 77.213µs | 127.0.0.1 | HEAD "/"
- 2025-11-20T09:53:51.857864-07:00 granite ollama[32079]: time=2025-11-20T09:53:51.857-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:51.858988-07:00 granite ollama[32079]: [GIN] 2025/11/20 - 09:53:51 | 200 | 144.967232ms | 127.0.0.1 | POST "/api/show"
- 2025-11-20T09:53:52.033861-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.033-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:52.034374-07:00 granite ollama[32079]: [GIN] 2025/11/20 - 09:53:52 | 200 | 172.377581ms | 127.0.0.1 | POST "/api/show"
- 2025-11-20T09:53:52.458203-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.457-07:00 level=TRACE source=sched.go:146 msg="processing incoming request" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:52.458514-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.457-07:00 level=TRACE source=sched.go:179 msg="refreshing GPU list" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:52.458562-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.457-07:00 level=DEBUG source=runner.go:250 msg="refreshing free memory"
- 2025-11-20T09:53:52.458594-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.457-07:00 level=DEBUG source=runner.go:314 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
- 2025-11-20T09:53:52.458623-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.458-07:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extraEnvs=map[]
- 2025-11-20T09:53:52.458669-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.458-07:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41101"
- 2025-11-20T09:53:52.458699-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.458-07:00 level=DEBUG source=server.go:393 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:52.473402-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.473-07:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
- 2025-11-20T09:53:52.477725-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.477-07:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:41101"
- 2025-11-20T09:53:52.480517-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
- 2025-11-20T09:53:52.480555-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
- 2025-11-20T09:53:52.480583-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:52.480652-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:52.480707-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
- 2025-11-20T09:53:52.480743-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
- 2025-11-20T09:53:52.480766-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
- 2025-11-20T09:53:52.480794-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
- 2025-11-20T09:53:52.480821-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.480-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
- 2025-11-20T09:53:52.487543-07:00 granite ollama[32079]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu.so
- 2025-11-20T09:53:52.487657-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.487-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:52.733701-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
- 2025-11-20T09:53:52.733789-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
- 2025-11-20T09:53:52.733816-07:00 granite ollama[32079]: ggml_cuda_init: found 1 CUDA devices:
- 2025-11-20T09:53:52.744423-07:00 granite ollama[32079]: Device 0: NVIDIA Thor, compute capability 11.0, VMM: yes, ID: GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600
- 2025-11-20T09:53:52.754079-07:00 granite ollama[32079]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
- 2025-11-20T09:53:52.754347-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
- 2025-11-20T09:53:52.754391-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:52.754457-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
- 2025-11-20T09:53:52.754508-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
- 2025-11-20T09:53:52.754569-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
- 2025-11-20T09:53:52.754619-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
- 2025-11-20T09:53:52.754665-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
- 2025-11-20T09:53:52.754738-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
- 2025-11-20T09:53:52.754768-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
- 2025-11-20T09:53:52.754797-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
- 2025-11-20T09:53:52.754832-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
- 2025-11-20T09:53:52.754861-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
- 2025-11-20T09:53:52.754888-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
- 2025-11-20T09:53:52.754916-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
- 2025-11-20T09:53:52.754965-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
- 2025-11-20T09:53:52.754988-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
- 2025-11-20T09:53:52.755018-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
- 2025-11-20T09:53:52.755046-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
- 2025-11-20T09:53:52.755073-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
- 2025-11-20T09:53:52.755100-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
- 2025-11-20T09:53:52.755127-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
- 2025-11-20T09:53:52.755154-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
- 2025-11-20T09:53:52.755186-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
- 2025-11-20T09:53:52.755215-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.754-07:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=274.347355ms
- 2025-11-20T09:53:52.767547-07:00 granite ollama[32079]: ggml_nvml_get_device_memory NVML not supported for memory query, using system memory (total=131882475520, available=98745761792)
- 2025-11-20T09:53:52.767666-07:00 granite ollama[32079]: ggml_backend_cuda_device_get_memory device GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 utilizing NVML memory reporting free: 98745761792 total: 131882475520
- 2025-11-20T09:53:52.771930-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.771-07:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=16.977188ms
- 2025-11-20T09:53:52.772431-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" devices="[{DeviceID:{ID:GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 Library:CUDA} Name:CUDA0 Description:NVIDIA Thor FilterID: Integrated:true PCIID:0000:01:00.0 TotalMemory:131882475520 FreeMemory:98745761792 ComputeMajor:11 ComputeMinor:0 DriverMajor:13 DriverMinor:0 LibraryPath:[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]}]"
- 2025-11-20T09:53:52.772590-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=314.189942ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[]
- 2025-11-20T09:53:52.772631-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=314.267867ms
- 2025-11-20T09:53:52.772662-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=TRACE source=sched.go:182 msg="refreshing system information" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:52.772690-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=TRACE source=gpu.go:22 msg="performing CPU discovery"
- 2025-11-20T09:53:52.772915-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=TRACE source=gpu.go:25 msg="CPU discovery completed" duration=602.684µs
- 2025-11-20T09:53:52.772963-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=DEBUG source=sched.go:194 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
- 2025-11-20T09:53:52.773005-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.772-07:00 level=TRACE source=sched.go:198 msg="loading model metadata" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:52.839834-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.838-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:52.840336-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.839-07:00 level=TRACE source=sched.go:206 msg="updating free space" gpu_count=1 model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:52.840371-07:00 granite ollama[32079]: time=2025-11-20T09:53:52.839-07:00 level=DEBUG source=sched.go:211 msg="loading first model" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3
- 2025-11-20T09:53:53.090671-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.090-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:53.091668-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.091-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=gptoss.pooling_type default=0
- 2025-11-20T09:53:53.091813-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.091-07:00 level=INFO source=server.go:209 msg="enabling flash attention"
- 2025-11-20T09:53:53.092206-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.091-07:00 level=INFO source=server.go:392 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3 --port 41093"
- 2025-11-20T09:53:53.092333-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.091-07:00 level=DEBUG source=server.go:393 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:53.092825-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=INFO source=sched.go:443 msg="system memory" total="122.8 GiB" free="92.0 GiB" free_swap="0 B"
- 2025-11-20T09:53:53.093437-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 library=CUDA available="91.5 GiB" free="92.0 GiB" minimum="457.0 MiB" overhead="0 B"
- 2025-11-20T09:53:53.093477-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=INFO source=server.go:702 msg="loading model" "model layers"=37 requested=-1
- 2025-11-20T09:53:53.093509-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=0 size="0 B"
- 2025-11-20T09:53:53.093559-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=1 size="0 B"
- 2025-11-20T09:53:53.093590-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=2 size="0 B"
- 2025-11-20T09:53:53.093619-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=3 size="0 B"
- 2025-11-20T09:53:53.093657-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=4 size="0 B"
- 2025-11-20T09:53:53.093688-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=5 size="0 B"
- 2025-11-20T09:53:53.093719-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=6 size="0 B"
- 2025-11-20T09:53:53.094204-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=7 size="0 B"
- 2025-11-20T09:53:53.094239-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=8 size="0 B"
- 2025-11-20T09:53:53.094269-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=9 size="0 B"
- 2025-11-20T09:53:53.094299-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=10 size="0 B"
- 2025-11-20T09:53:53.094328-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=11 size="0 B"
- 2025-11-20T09:53:53.094357-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=12 size="0 B"
- 2025-11-20T09:53:53.094388-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=13 size="0 B"
- 2025-11-20T09:53:53.094457-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=14 size="0 B"
- 2025-11-20T09:53:53.094489-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=15 size="0 B"
- 2025-11-20T09:53:53.094514-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=16 size="0 B"
- 2025-11-20T09:53:53.094542-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=17 size="0 B"
- 2025-11-20T09:53:53.094572-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=18 size="0 B"
- 2025-11-20T09:53:53.094606-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=19 size="0 B"
- 2025-11-20T09:53:53.094635-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=20 size="0 B"
- 2025-11-20T09:53:53.094659-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=21 size="0 B"
- 2025-11-20T09:53:53.094689-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=22 size="0 B"
- 2025-11-20T09:53:53.094718-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=23 size="0 B"
- 2025-11-20T09:53:53.094748-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=24 size="0 B"
- 2025-11-20T09:53:53.094772-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=25 size="0 B"
- 2025-11-20T09:53:53.094801-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=26 size="0 B"
- 2025-11-20T09:53:53.094836-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=27 size="0 B"
- 2025-11-20T09:53:53.094869-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=28 size="0 B"
- 2025-11-20T09:53:53.094898-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=29 size="0 B"
- 2025-11-20T09:53:53.094932-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=30 size="0 B"
- 2025-11-20T09:53:53.094972-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=31 size="0 B"
- 2025-11-20T09:53:53.095014-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=32 size="0 B"
- 2025-11-20T09:53:53.095043-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=33 size="0 B"
- 2025-11-20T09:53:53.095072-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=34 size="0 B"
- 2025-11-20T09:53:53.095101-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=35 size="0 B"
- 2025-11-20T09:53:53.095133-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.092-07:00 level=TRACE source=server.go:896 msg="layer to assign" layer=36 size="0 B"
- 2025-11-20T09:53:53.106461-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.106-07:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
- 2025-11-20T09:53:53.110548-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.110-07:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:41093"
- 2025-11-20T09:53:53.115897-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.115-07:00 level=INFO source=runner.go:1271 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:8192 KvCacheType: NumThreads:14 GPULayers:37[ID:GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
- 2025-11-20T09:53:53.182713-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.182-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
- 2025-11-20T09:53:53.183248-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.182-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
- 2025-11-20T09:53:53.183427-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.182-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
- 2025-11-20T09:53:53.183464-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.182-07:00 level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=471 num_key_values=30
- 2025-11-20T09:53:53.183495-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.182-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
- 2025-11-20T09:53:53.188782-07:00 granite ollama[32079]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu.so
- 2025-11-20T09:53:53.188897-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.188-07:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12
- 2025-11-20T09:53:53.427452-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
- 2025-11-20T09:53:53.427567-07:00 granite ollama[32079]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
- 2025-11-20T09:53:53.427602-07:00 granite ollama[32079]: ggml_cuda_init: found 1 CUDA devices:
- 2025-11-20T09:53:53.436667-07:00 granite ollama[32079]: Device 0: NVIDIA Thor, compute capability 11.0, VMM: yes, ID: GPU-a7c66ad2-6dbb-0ab8-c1a2-37ba6dba3600
- 2025-11-20T09:53:53.446082-07:00 granite ollama[32079]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
- 2025-11-20T09:53:53.446187-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.445-07:00 level=INFO source=ggml.go:104 msg=system CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.LLAMAFILE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
- 2025-11-20T09:53:53.446247-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.445-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446280-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446333-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446362-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446391-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446420-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446450-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446479-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.446518-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446546-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446575-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446621-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.446650-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.0.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446679-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446708-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446736-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446765-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446792-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446825-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446859-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446888-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.446911-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446938-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.446965-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447017-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447041-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.1.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447070-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447098-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447131-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447162-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447190-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447216-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447243-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447270-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447297-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447325-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447375-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447402-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447431-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.2.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447462-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447489-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447515-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447542-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447569-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447599-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447626-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447649-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447677-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447727-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447755-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447786-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447813-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.3.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.447840-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447867-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447894-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447921-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.447948-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.447975-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448001-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448029-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448082-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448110-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448137-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448164-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448191-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.4.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448218-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448245-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448271-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448298-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448322-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448352-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448379-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448426-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448453-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448480-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448507-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448533-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448560-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.5.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448588-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448614-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448638-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448668-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448695-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448721-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448772-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448816-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448847-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448874-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.448901-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.448928-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448952-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.6.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.448983-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449010-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449037-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449064-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449090-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449138-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449165-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449192-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449216-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449242-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449269-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449300-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.449324-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.7.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.449350-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449374-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449408-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449434-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449482-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449509-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449539-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449566-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449602-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449633-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449660-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449687-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.449711-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.8.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.449737-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449764-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449790-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449835-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449858-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449888-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449915-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449941-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.449968-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.449998-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450025-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450052-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450078-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.9.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450109-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450135-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450181-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450209-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450235-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450262-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450289-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450315-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450342-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450369-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450395-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450421-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450452-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.10.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450475-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450520-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450547-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450571-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450598-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450625-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450652-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.446-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450675-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450702-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450729-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450759-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450783-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450815-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.11.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.450862-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450888-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450912-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450938-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.450965-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.450991-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451018-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451049-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451073-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451101-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451127-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451154-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451204-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.12.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451228-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451255-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451278-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451304-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451335-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451358-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451384-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451408-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451431-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451454-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451480-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451528-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451555-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.13.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451582-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451605-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451633-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451656-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451683-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451709-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451736-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451762-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451789-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451819-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.451868-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451895-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451926-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.14.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.451952-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.451976-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452003-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452029-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452055-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452082-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452109-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452136-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452163-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452215-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452243-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452270-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.452297-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.15.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.452324-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452350-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452373-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452400-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452428-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452451-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452478-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452509-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452553-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452577-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452603-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452630-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.452656-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.16.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.452683-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452709-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.452736-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.452759-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.453837-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.454545-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.454593-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.454666-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.454712-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.454755-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.454794-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.454841-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.454880-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.17.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.454923-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.454967-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455015-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455058-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455098-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455136-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455198-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455238-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455276-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455314-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455355-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455391-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.455430-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.18.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.455465-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455504-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455544-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455588-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455627-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455685-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455726-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455765-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455804-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455844-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.455884-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.455927-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.455967-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.19.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.456007-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456045-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456083-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456122-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456177-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456214-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456249-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456292-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456335-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456370-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456406-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456441-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.456477-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.20.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.456512-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456551-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456593-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456652-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456697-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456737-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456776-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456825-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456863-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456899-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.456934-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.456969-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.457005-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.21.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.457043-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457085-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457144-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457184-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457220-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457259-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457297-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457336-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.447-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457376-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457418-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457457-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457493-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.457535-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.22.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.457570-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457629-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457668-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457706-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457744-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457782-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457816-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457850-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.457888-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457927-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.457963-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458002-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.458036-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.23.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.458091-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458130-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458169-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458207-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458245-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458282-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458324-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458363-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458398-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458432-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458470-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458508-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.458568-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.24.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.458607-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458645-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458679-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458717-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458759-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458797-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458840-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458875-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.458922-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.458975-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459019-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459076-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.459119-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.25.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.459158-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459204-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459245-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459287-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459328-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459366-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459407-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459449-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459491-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459529-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459597-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459644-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.459686-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.26.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.459728-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459766-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459807-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459845-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459883-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.459925-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.459963-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460001-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460043-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460110-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460153-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460191-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.460230-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.27.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.460271-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460310-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460352-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460398-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460436-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460477-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460522-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460564-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460622-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460667-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460705-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460747-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.460785-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.28.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.460833-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460871-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.460916-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.460965-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461004-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461042-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461083-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461146-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461189-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461231-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461272-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461314-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.461357-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.29.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.461395-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461440-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461485-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461527-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461568-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461606-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461663-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461702-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461743-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461784-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.461822-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.461872-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.461940-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.30.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.461980-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462018-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462060-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462103-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462141-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462200-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462239-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462281-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462320-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462361-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462406-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462445-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.462483-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.31.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.462528-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462570-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462617-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462655-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462715-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462758-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462796-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462835-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.462873-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462914-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.462956-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463001-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.463039-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.32.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.463084-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.448-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463126-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463167-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463228-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463270-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463308-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463349-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463395-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463440-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463479-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463517-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463556-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.463597-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.33.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.463635-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463676-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463733-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463774-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463813-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.463854-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463900-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463942-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.463979-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464017-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464058-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464099-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.464138-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.34.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.464189-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464248-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_out.bias shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464287-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_out.weight shape="[4096 2880]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464329-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_qkv.bias shape=[5120] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464370-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_qkv.weight shape="[2880 5120]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464411-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.attn_sinks shape=[64] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464449-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_gate_inp.bias shape=[128] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464490-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_gate_inp.weight shape="[2880 128]" dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464532-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_gate_up_exps.bias shape="[5760 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464570-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_down_exps.bias shape="[2880 128]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464611-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464649-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_gate_up_exps.weight shape="[2880 5760 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.464691-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=blk.35.ffn_down_exps.weight shape="[2880 2880 128]" dtype=4 buffer_type=CUDA0
- 2025-11-20T09:53:53.464752-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=output.weight shape="[2880 201088]" dtype=30 buffer_type=CUDA0
- 2025-11-20T09:53:53.464798-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=output_norm.weight shape=[2880] dtype=0 buffer_type=CUDA0
- 2025-11-20T09:53:53.464839-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:279 msg="created tensor" name=token_embd.weight shape="[2880 201088]" dtype=30 buffer_type=CPU
- 2025-11-20T09:53:53.464877-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:418 msg="model weights" buffer=CPU size="1.1 GiB"
- 2025-11-20T09:53:53.464914-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=ggml.go:418 msg="model weights" buffer=CUDA0 size="59.8 GiB"
- 2025-11-20T09:53:53.464952-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=gptoss.pooling_type default=0
- 2025-11-20T09:53:53.464990-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=model.go:215 msg="found tensor" name=token_embd.weight type=bf16 shape="[2880 201088]"
- 2025-11-20T09:53:53.465034-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.465073-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.465114-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.465151-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.449-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.465196-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.465234-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.465275-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.465335-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.465383-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.465421-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.465462-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.465500-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.465538-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.0.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.465579-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.465617-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.465662-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.465704-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.465742-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.465780-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.465821-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.465862-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.465921-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.465960-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.466002-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.466040-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.466086-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.1.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.466128-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.466166-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.466204-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.466244-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.466285-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.466326-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.466368-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.466409-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.466450-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.466497-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.466545-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.466587-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.466626-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.2.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.466663-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.466701-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.466746-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.466784-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.466822-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.466860-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.466900-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.466938-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.466976-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.467018-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.467078-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.467118-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.467156-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.3.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.467193-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.467231-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.467271-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.467309-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.467347-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.467384-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.467422-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.467467-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.467505-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.467542-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.467580-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.467638-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.467676-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.4.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.467713-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.467751-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.467791-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.467832-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.467873-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.467915-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.467954-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.467995-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.468034-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.468072-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.468110-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.468152-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.468217-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.5.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.468257-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.468295-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.468336-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.468386-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.468425-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.468466-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.468505-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.468543-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.468590-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.468632-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.468671-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.468712-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.468755-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.6.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.468819-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.468866-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.468911-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.468953-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.468995-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.469034-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.469079-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.469121-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.469163-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.469205-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.469247-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.469286-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.469333-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.7.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.469375-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.469437-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.469480-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.450-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.469518-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.469557-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.469595-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.469637-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.469678-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.469720-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.469758-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.469800-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.469839-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.469881-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.8.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.469918-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.469956-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.470021-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.470060-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.470102-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.470150-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.470191-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.470233-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.470278-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.470317-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.470355-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.470393-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.470434-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.9.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.470472-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.470510-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.470550-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.470594-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.470632-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.470670-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.470715-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.470753-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.470861-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.470910-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.470960-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.471009-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.471059-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.10.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.471104-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.471148-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.471192-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.471239-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.471302-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.471352-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.471396-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.471440-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.471487-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.471535-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.471582-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.471630-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.471673-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.11.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.471720-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.471787-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.471831-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.471875-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.471926-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.471995-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.472044-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.472088-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.472136-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.472184-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.472229-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.472273-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.472323-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.12.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.472367-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.472410-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.472453-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.472500-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.472543-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.472586-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.472652-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.472701-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.472744-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.472803-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.472866-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.472905-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.472959-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.13.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.472994-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.473037-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.473082-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.473118-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.473170-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.473196-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.473218-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.473289-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.473316-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.473342-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.473368-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.473392-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.473415-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.14.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.473440-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.473463-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.473488-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.473511-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.473533-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.473563-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.473589-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.473622-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.473655-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.473678-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.473704-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.473725-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.473747-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.15.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.473799-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.473821-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.473843-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.451-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.474301-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.474385-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.474429-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.474468-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.474507-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.474546-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.474617-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.474662-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.474700-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.474738-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.16.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.474775-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.474821-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.474865-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.474903-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.474941-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.474980-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.475022-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.475063-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.475101-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.475143-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.475212-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.475259-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.475298-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.17.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.475340-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.475379-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.475421-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.475471-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.475513-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.475551-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.475592-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.475630-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.475667-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.475713-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.475755-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.475813-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.475856-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.18.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.475895-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.475936-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.475978-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.476016-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.476054-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.476094-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.476132-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.476174-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.476220-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.476261-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.476302-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.476340-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.476389-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.19.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.476431-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.476472-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.476513-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.476550-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.476593-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.476639-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.476681-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.476719-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.476757-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.476805-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.476845-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.476883-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.476939-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.20.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.476992-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477031-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.477069-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.477123-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.477166-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.477208-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.477250-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477274-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.477298-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.477325-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.477349-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.477377-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.477400-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.21.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.477429-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477481-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.477504-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.477528-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.477551-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.477574-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.477597-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477626-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.477653-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.477676-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.477704-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.477731-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.477759-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.22.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.477782-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477805-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.477854-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.477881-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.477904-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.477931-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.477954-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.477977-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478004-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.478027-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.478060-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.478089-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.478113-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.23.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478136-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.478159-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.478182-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.478230-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.478253-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.478283-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.478312-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.478341-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.452-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478373-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.478402-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.478429-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.478453-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.478481-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.24.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478504-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.478531-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.478554-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.478583-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.478629-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.478652-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.478685-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.478708-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478736-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.478765-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.478794-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.478817-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.478845-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.25.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.478879-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.478916-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.478946-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.478973-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.479000-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.479045-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.479072-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479095-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479118-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.479140-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.479167-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.479190-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.479217-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.26.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479241-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479264-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.479287-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.479310-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.479336-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.479359-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.479405-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479432-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479455-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.479481-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.479509-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.479533-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.479559-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.27.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479586-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479612-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.479635-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.479658-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.479681-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.479704-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.479731-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479758-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479785-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.479809-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.479832-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.479859-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.479885-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.28.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.479908-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.479932-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.479958-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.479982-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.480005-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.480056-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.480083-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.480110-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480147-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.480170-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.480193-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.480217-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.480244-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.29.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480267-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.480290-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.480314-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.480336-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.480367-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.480390-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.480413-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.480436-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480460-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.480516-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.480543-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.480566-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.480590-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.30.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480613-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.480637-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.480668-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.480691-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.480722-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.480745-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.480772-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.480805-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480828-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.480852-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.480897-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.480920-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.480950-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.31.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.480981-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.481004-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.481031-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.481055-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.481078-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.481105-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.481128-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.481155-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.481179-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.481206-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.481232-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.481290-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.481347-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.32.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.481382-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.481415-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.481446-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.453-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.481481-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.481513-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.481547-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.481582-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.481616-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.481653-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.481689-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.481720-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.481751-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.481802-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.33.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.481835-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.481867-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.481898-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.481929-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.481960-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.481991-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.482029-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.482067-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.482102-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.482134-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.482168-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.482204-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.482238-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.34.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.482288-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.482324-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_qkv.weight type=bf16 shape="[2880 5120]"
- 2025-11-20T09:53:53.482355-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_qkv.bias type=f32 shape=[5120]
- 2025-11-20T09:53:53.482387-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_out.weight type=bf16 shape="[4096 2880]"
- 2025-11-20T09:53:53.482418-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_out.bias type=f32 shape=[2880]
- 2025-11-20T09:53:53.482456-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.attn_sinks type=f32 shape=[64]
- 2025-11-20T09:53:53.482488-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.482519-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_gate_inp.weight type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.482554-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_gate_inp.bias type=f32 shape=[128]
- 2025-11-20T09:53:53.482586-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_gate_up_exps.weight type=mxfp4 shape="[2880 5760 128]"
- 2025-11-20T09:53:53.482622-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_gate_up_exps.bias type=f32 shape="[5760 128]"
- 2025-11-20T09:53:53.482654-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_down_exps.weight type=mxfp4 shape="[2880 2880 128]"
- 2025-11-20T09:53:53.482685-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=blk.35.ffn_down_exps.bias type=f32 shape="[2880 128]"
- 2025-11-20T09:53:53.482717-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=output_norm.weight type=f32 shape=[2880]
- 2025-11-20T09:53:53.482754-07:00 granite ollama[32079]: time=2025-11-20T09:53:53.454-07:00 level=TRACE source=model.go:215 msg="found tensor" name=output.weight type=bf16 shape="[2880 201088]"
- 2025-11-20T09:53:53.646805-07:00 granite ollama[32079]: CUDA error: an internal operation failed
- 2025-11-20T09:53:53.646976-07:00 granite ollama[32079]: current device: 0, in function cublas_handle at //ml/backend/ggml/ggml/src/ggml-cuda/common.cuh:1020
- 2025-11-20T09:53:53.647030-07:00 granite ollama[32079]: cublasCreate_v2(&cublas_handles[device])
- 2025-11-20T09:53:53.647073-07:00 granite ollama[32079]: //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:88: CUDA error
- 2025-11-20T09:53:53.719654-07:00 granite ollama[32079]: [New LWP 32181]
- 2025-11-20T09:53:53.719755-07:00 granite ollama[32079]: [New LWP 32180]
- 2025-11-20T09:53:53.719779-07:00 granite ollama[32079]: [New LWP 32179]
- 2025-11-20T09:53:53.719797-07:00 granite ollama[32079]: [New LWP 32175]
- 2025-11-20T09:53:53.719815-07:00 granite ollama[32079]: [New LWP 32174]
- 2025-11-20T09:53:53.719832-07:00 granite ollama[32079]: [New LWP 32173]
- 2025-11-20T09:53:53.719848-07:00 granite ollama[32079]: [New LWP 32172]
- 2025-11-20T09:53:53.719867-07:00 granite ollama[32079]: [New LWP 32169]
- 2025-11-20T09:53:53.719886-07:00 granite ollama[32079]: [New LWP 32168]
- 2025-11-20T09:53:53.719904-07:00 granite ollama[32079]: [New LWP 32167]
- 2025-11-20T09:53:53.719921-07:00 granite ollama[32079]: [New LWP 32166]
- 2025-11-20T09:53:53.719937-07:00 granite ollama[32079]: [New LWP 32165]
- 2025-11-20T09:53:53.719953-07:00 granite ollama[32079]: [New LWP 32164]
- 2025-11-20T09:53:53.719969-07:00 granite ollama[32079]: [New LWP 32163]
- 2025-11-20T09:53:53.719985-07:00 granite ollama[32079]: [New LWP 32162]
- 2025-11-20T09:53:53.720008-07:00 granite ollama[32079]: [New LWP 32161]
- 2025-11-20T09:53:53.953067-07:00 granite ollama[32079]: [Thread debugging using libthread_db enabled]
- 2025-11-20T09:53:53.953183-07:00 granite ollama[32079]: Using host libthread_db library "/lib/aarch64-linux-gnu/libthread_db.so.1".
- 2025-11-20T09:53:53.953208-07:00 granite ollama[32079]: 0x0000aaaad08021ac in ?? ()
- 2025-11-20T09:53:53.953635-07:00 granite ollama[32079]: #0 0x0000aaaad08021ac in ?? ()
- 2025-11-20T09:53:53.953662-07:00 granite ollama[32079]: #1 0x0000000000000080 in ?? ()
- 2025-11-20T09:53:53.959426-07:00 granite ollama[32079]: Backtrace stopped: previous frame identical to this frame (corrupt stack?)
- 2025-11-20T09:53:53.959449-07:00 granite ollama[32079]: [Inferior 1 (process 32160) detached]
- 2025-11-20T09:53:53.983578-07:00 granite ollama[32079]: SIGABRT: abort
- 2025-11-20T09:53:53.983666-07:00 granite ollama[32079]: PC=0xffffa1eb7608 m=13 sigcode=18446744073709551610
- 2025-11-20T09:53:53.983735-07:00 granite ollama[32079]: signal arrived during cgo execution
- 2025-11-20T09:53:53.983790-07:00 granite ollama[32079]: goroutine 13 gp=0x4000505500 m=13 mp=0x400030e008 [syscall]:
- 2025-11-20T09:53:53.983831-07:00 granite ollama[32079]: runtime.cgocall(0xaaaad13547b4, 0x40000430c8)
- 2025-11-20T09:53:53.983886-07:00 granite ollama[32079]: #011runtime/cgocall.go:167 +0x44 fp=0x4000043080 sp=0x4000043040 pc=0xaaaad07f5954
- 2025-11-20T09:53:53.983954-07:00 granite ollama[32079]: github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0xffff38782c50, 0xfffe8c941d20)
- 2025-11-20T09:53:53.983995-07:00 granite ollama[32079]: #011_cgo_gotypes.go:996 +0x34 fp=0x40000430c0 sp=0x4000043080 pc=0xaaaad0bcac14
- 2025-11-20T09:53:53.984058-07:00 granite ollama[32079]: github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve.func2(...)
- 2025-11-20T09:53:53.984128-07:00 granite ollama[32079]: #011github.com/ollama/ollama/ml/backend/ggml/ggml.go:850
- 2025-11-20T09:53:53.984174-07:00 granite ollama[32079]: github.com/ollama/ollama/ml/backend/ggml.(*Context).Reserve(0x4001a7afc0)
- 2025-11-20T09:53:53.984223-07:00 granite ollama[32079]: #011github.com/ollama/ollama/ml/backend/ggml/ggml.go:850 +0xe0 fp=0x4000043350 sp=0x40000430c0 pc=0xaaaad0bd4be0
- 2025-11-20T09:53:53.984277-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.(*Server).reserveWorstCaseGraph(0x4000234b40, 0x1)
- 2025-11-20T09:53:53.984317-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1162 +0x834 fp=0x4000043680 sp=0x4000043350 pc=0xaaaad0c7ec24
- 2025-11-20T09:53:53.984366-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x4000234b40, {0xffffd1694dad?, 0x0?}, {0x0, 0xe, {0x40005b4140, 0x1, 0x1}, 0x1}, {0x0?, ...}, ...)
- 2025-11-20T09:53:53.984406-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1219 +0x230 fp=0x4000043710 sp=0x4000043680 pc=0xaaaad0c7f240
- 2025-11-20T09:53:53.984606-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x4000234b40, {0xaaaad1b29ac0, 0x40001d2460}, 0x400037e000)
- 2025-11-20T09:53:53.984649-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1298 +0x460 fp=0x4000043aa0 sp=0x4000043710 pc=0xaaaad0c7fb50
- 2025-11-20T09:53:53.984703-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0xaaaad1b29ac0?, 0x40001d2460?}, 0x40004f7b28?)
- 2025-11-20T09:53:53.984752-07:00 granite ollama[32079]: #011<autogenerated>:1 +0x40 fp=0x4000043ad0 sp=0x4000043aa0 pc=0xaaaad0c81a50
- 2025-11-20T09:53:53.984819-07:00 granite ollama[32079]: net/http.HandlerFunc.ServeHTTP(0x4000545740?, {0xaaaad1b29ac0?, 0x40001d2460?}, 0x40004f7b10?)
- 2025-11-20T09:53:53.984863-07:00 granite ollama[32079]: #011net/http/server.go:2294 +0x38 fp=0x4000043b00 sp=0x4000043ad0 pc=0xaaaad0ab1568
- 2025-11-20T09:53:53.984924-07:00 granite ollama[32079]: net/http.(*ServeMux).ServeHTTP(0x10?, {0xaaaad1b29ac0, 0x40001d2460}, 0x400037e000)
- 2025-11-20T09:53:53.984980-07:00 granite ollama[32079]: #011net/http/server.go:2822 +0x1b4 fp=0x4000043b50 sp=0x4000043b00 pc=0xaaaad0ab30f4
- 2025-11-20T09:53:53.985020-07:00 granite ollama[32079]: net/http.serverHandler.ServeHTTP({0xaaaad1b260b0?}, {0xaaaad1b29ac0?, 0x40001d2460?}, 0x1?)
- 2025-11-20T09:53:53.985073-07:00 granite ollama[32079]: #011net/http/server.go:3301 +0xbc fp=0x4000043b80 sp=0x4000043b50 pc=0xaaaad0aceddc
- 2025-11-20T09:53:53.985121-07:00 granite ollama[32079]: net/http.(*conn).serve(0x40004bc3f0, {0xaaaad1b2bec8, 0x4000686930})
- 2025-11-20T09:53:53.985164-07:00 granite ollama[32079]: #011net/http/server.go:2102 +0x52c fp=0x4000043fa0 sp=0x4000043b80 pc=0xaaaad0aafd0c
- 2025-11-20T09:53:53.985214-07:00 granite ollama[32079]: net/http.(*Server).Serve.gowrap3()
- 2025-11-20T09:53:53.985261-07:00 granite ollama[32079]: #011net/http/server.go:3454 +0x30 fp=0x4000043fd0 sp=0x4000043fa0 pc=0xaaaad0ab4ed0
- 2025-11-20T09:53:53.985312-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.985365-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x4000043fd0 sp=0x4000043fd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.985404-07:00 granite ollama[32079]: created by net/http.(*Server).Serve in goroutine 1
- 2025-11-20T09:53:53.985455-07:00 granite ollama[32079]: #011net/http/server.go:3454 +0x3d8
- 2025-11-20T09:53:53.985503-07:00 granite ollama[32079]: goroutine 1 gp=0x40000021c0 m=nil [IO wait]:
- 2025-11-20T09:53:53.985542-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.985594-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4001405720 sp=0x4001405700 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.985634-07:00 granite ollama[32079]: runtime.netpollblock(0x7000000000?, 0x6?, 0x0?)
- 2025-11-20T09:53:53.985686-07:00 granite ollama[32079]: #011runtime/netpoll.go:575 +0x158 fp=0x4001405760 sp=0x4001405720 pc=0xaaaad07bde28
- 2025-11-20T09:53:53.985735-07:00 granite ollama[32079]: internal/poll.runtime_pollWait(0xffffa1c86f30, 0x72)
- 2025-11-20T09:53:53.985778-07:00 granite ollama[32079]: #011runtime/netpoll.go:351 +0xa0 fp=0x4001405790 sp=0x4001405760 pc=0xaaaad07f8020
- 2025-11-20T09:53:53.985830-07:00 granite ollama[32079]: internal/poll.(*pollDesc).wait(0x4000490200?, 0xaaaad0880e58?, 0x0)
- 2025-11-20T09:53:53.985868-07:00 granite ollama[32079]: #011internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40014057c0 sp=0x4001405790 pc=0xaaaad087a3f8
- 2025-11-20T09:53:53.985918-07:00 granite ollama[32079]: internal/poll.(*pollDesc).waitRead(...)
- 2025-11-20T09:53:53.986080-07:00 granite ollama[32079]: #011internal/poll/fd_poll_runtime.go:89
- 2025-11-20T09:53:53.986130-07:00 granite ollama[32079]: internal/poll.(*FD).Accept(0x4000490200)
- 2025-11-20T09:53:53.986169-07:00 granite ollama[32079]: #011internal/poll/fd_unix.go:620 +0x24c fp=0x4001405870 sp=0x40014057c0 pc=0xaaaad087eccc
- 2025-11-20T09:53:53.986218-07:00 granite ollama[32079]: net.(*netFD).accept(0x4000490200)
- 2025-11-20T09:53:53.986271-07:00 granite ollama[32079]: #011net/fd_unix.go:172 +0x28 fp=0x4001405930 sp=0x4001405870 pc=0xaaaad08ed658
- 2025-11-20T09:53:53.986310-07:00 granite ollama[32079]: net.(*TCPListener).accept(0x40004207c0)
- 2025-11-20T09:53:53.986368-07:00 granite ollama[32079]: #011net/tcpsock_posix.go:159 +0x24 fp=0x4001405980 sp=0x4001405930 pc=0xaaaad0902574
- 2025-11-20T09:53:53.986419-07:00 granite ollama[32079]: net.(*TCPListener).Accept(0x40004207c0)
- 2025-11-20T09:53:53.986458-07:00 granite ollama[32079]: #011net/tcpsock.go:380 +0x2c fp=0x40014059c0 sp=0x4001405980 pc=0xaaaad090150c
- 2025-11-20T09:53:53.986510-07:00 granite ollama[32079]: net/http.(*onceCloseListener).Accept(0x40004bc3f0?)
- 2025-11-20T09:53:53.986556-07:00 granite ollama[32079]: #011<autogenerated>:1 +0x30 fp=0x40014059e0 sp=0x40014059c0 pc=0xaaaad0adb400
- 2025-11-20T09:53:53.986605-07:00 granite ollama[32079]: net/http.(*Server).Serve(0x4000201600, {0xaaaad1b298e0, 0x40004207c0})
- 2025-11-20T09:53:53.986657-07:00 granite ollama[32079]: #011net/http/server.go:3424 +0x290 fp=0x4001405b10 sp=0x40014059e0 pc=0xaaaad0ab4b40
- 2025-11-20T09:53:53.986837-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.Execute({0x4000032110, 0x4, 0x4})
- 2025-11-20T09:53:53.986890-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1434 +0x7fc fp=0x4001405ce0 sp=0x4001405b10 pc=0xaaaad0c8147c
- 2025-11-20T09:53:53.986930-07:00 granite ollama[32079]: github.com/ollama/ollama/runner.Execute({0x40000320f0?, 0x0?, 0x0?})
- 2025-11-20T09:53:53.986965-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/runner.go:20 +0x120 fp=0x4001405d10 sp=0x4001405ce0 pc=0xaaaad0c81d70
- 2025-11-20T09:53:53.987005-07:00 granite ollama[32079]: github.com/ollama/ollama/cmd.NewCLI.func2(0x4000201400?, {0xaaaad16210aa?, 0x4?, 0xaaaad16210ae?})
- 2025-11-20T09:53:53.987040-07:00 granite ollama[32079]: #011github.com/ollama/ollama/cmd/cmd.go:1841 +0x54 fp=0x4001405d40 sp=0x4001405d10 pc=0xaaaad13047c4
- 2025-11-20T09:53:53.987064-07:00 granite ollama[32079]: github.com/spf13/cobra.(*Command).execute(0x40004c1508, {0x400037c370, 0x5, 0x5})
- 2025-11-20T09:53:53.987088-07:00 granite ollama[32079]: #011github.com/spf13/[email protected]/command.go:940 +0x648 fp=0x4001405e60 sp=0x4001405d40 pc=0xaaaad095ca58
- 2025-11-20T09:53:53.987114-07:00 granite ollama[32079]: github.com/spf13/cobra.(*Command).ExecuteC(0x4000690f08)
- 2025-11-20T09:53:53.987142-07:00 granite ollama[32079]: #011github.com/spf13/[email protected]/command.go:1068 +0x320 fp=0x4001405f20 sp=0x4001405e60 pc=0xaaaad095d1a0
- 2025-11-20T09:53:53.987165-07:00 granite ollama[32079]: github.com/spf13/cobra.(*Command).Execute(...)
- 2025-11-20T09:53:53.987197-07:00 granite ollama[32079]: #011github.com/spf13/[email protected]/command.go:992
- 2025-11-20T09:53:53.987221-07:00 granite ollama[32079]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
- 2025-11-20T09:53:53.987244-07:00 granite ollama[32079]: #011github.com/spf13/[email protected]/command.go:985
- 2025-11-20T09:53:53.987266-07:00 granite ollama[32079]: main.main()
- 2025-11-20T09:53:53.987290-07:00 granite ollama[32079]: #011github.com/ollama/ollama/main.go:12 +0x54 fp=0x4001405f40 sp=0x4001405f20 pc=0xaaaad1305314
- 2025-11-20T09:53:53.987316-07:00 granite ollama[32079]: runtime.main()
- 2025-11-20T09:53:53.987458-07:00 granite ollama[32079]: #011runtime/proc.go:283 +0x284 fp=0x4001405fd0 sp=0x4001405f40 pc=0xaaaad07c51d4
- 2025-11-20T09:53:53.987485-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.987507-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x4001405fd0 sp=0x4001405fd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.987529-07:00 granite ollama[32079]: goroutine 2 gp=0x4000002c40 m=nil [force gc (idle)]:
- 2025-11-20T09:53:53.987555-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.987578-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007af90 sp=0x400007af70 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.987610-07:00 granite ollama[32079]: runtime.goparkunlock(...)
- 2025-11-20T09:53:53.987639-07:00 granite ollama[32079]: #011runtime/proc.go:441
- 2025-11-20T09:53:53.987661-07:00 granite ollama[32079]: runtime.forcegchelper()
- 2025-11-20T09:53:53.987684-07:00 granite ollama[32079]: #011runtime/proc.go:348 +0xb8 fp=0x400007afd0 sp=0x400007af90 pc=0xaaaad07c5528
- 2025-11-20T09:53:53.987707-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.987729-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007afd0 sp=0x400007afd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.987755-07:00 granite ollama[32079]: created by runtime.init.7 in goroutine 1
- 2025-11-20T09:53:53.987782-07:00 granite ollama[32079]: #011runtime/proc.go:336 +0x24
- 2025-11-20T09:53:53.987805-07:00 granite ollama[32079]: goroutine 3 gp=0x4000003180 m=nil [GC sweep wait]:
- 2025-11-20T09:53:53.987827-07:00 granite ollama[32079]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.987850-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007b760 sp=0x400007b740 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.987872-07:00 granite ollama[32079]: runtime.goparkunlock(...)
- 2025-11-20T09:53:53.987894-07:00 granite ollama[32079]: #011runtime/proc.go:441
- 2025-11-20T09:53:53.987915-07:00 granite ollama[32079]: runtime.bgsweep(0x40000a6000)
- 2025-11-20T09:53:53.987943-07:00 granite ollama[32079]: #011runtime/mgcsweep.go:316 +0x108 fp=0x400007b7b0 sp=0x400007b760 pc=0xaaaad07afd58
- 2025-11-20T09:53:53.987971-07:00 granite ollama[32079]: runtime.gcenable.gowrap1()
- 2025-11-20T09:53:53.987993-07:00 granite ollama[32079]: #011runtime/mgc.go:204 +0x28 fp=0x400007b7d0 sp=0x400007b7b0 pc=0xaaaad07a3b88
- 2025-11-20T09:53:53.988015-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.988037-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007b7d0 sp=0x400007b7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.988063-07:00 granite ollama[32079]: created by runtime.gcenable in goroutine 1
- 2025-11-20T09:53:53.988091-07:00 granite ollama[32079]: #011runtime/mgc.go:204 +0x6c
- 2025-11-20T09:53:53.988114-07:00 granite ollama[32079]: goroutine 4 gp=0x4000003340 m=nil [GC scavenge wait]:
- 2025-11-20T09:53:53.988137-07:00 granite ollama[32079]: runtime.gopark(0x10000?, 0xaaaad17e61d8?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.988164-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007bf60 sp=0x400007bf40 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.988192-07:00 granite ollama[32079]: runtime.goparkunlock(...)
- 2025-11-20T09:53:53.988213-07:00 granite ollama[32079]: #011runtime/proc.go:441
- 2025-11-20T09:53:53.988239-07:00 granite ollama[32079]: runtime.(*scavengerState).park(0xaaaad23a0080)
- 2025-11-20T09:53:53.988262-07:00 granite ollama[32079]: #011runtime/mgcscavenge.go:425 +0x5c fp=0x400007bf90 sp=0x400007bf60 pc=0xaaaad07ad81c
- 2025-11-20T09:53:53.988285-07:00 granite ollama[32079]: runtime.bgscavenge(0x40000a6000)
- 2025-11-20T09:53:53.988312-07:00 granite ollama[32079]: #011runtime/mgcscavenge.go:658 +0xac fp=0x400007bfb0 sp=0x400007bf90 pc=0xaaaad07add9c
- 2025-11-20T09:53:53.988335-07:00 granite ollama[32079]: runtime.gcenable.gowrap2()
- 2025-11-20T09:53:53.988358-07:00 granite ollama[32079]: #011runtime/mgc.go:205 +0x28 fp=0x400007bfd0 sp=0x400007bfb0 pc=0xaaaad07a3b28
- 2025-11-20T09:53:53.988380-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.988402-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007bfd0 sp=0x400007bfd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.988424-07:00 granite ollama[32079]: created by runtime.gcenable in goroutine 1
- 2025-11-20T09:53:53.988446-07:00 granite ollama[32079]: #011runtime/mgc.go:205 +0xac
- 2025-11-20T09:53:53.988599-07:00 granite ollama[32079]: goroutine 5 gp=0x4000003c00 m=nil [finalizer wait]:
- 2025-11-20T09:53:53.988622-07:00 granite ollama[32079]: runtime.gopark(0x18000001b8?, 0x1000000000000?, 0xf8?, 0xa5?, 0xaaaad0adde4c?)
- 2025-11-20T09:53:53.988645-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007a590 sp=0x400007a570 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.988668-07:00 granite ollama[32079]: runtime.runfinq()
- 2025-11-20T09:53:53.988690-07:00 granite ollama[32079]: #011runtime/mfinal.go:196 +0x108 fp=0x400007a7d0 sp=0x400007a590 pc=0xaaaad07a2b88
- 2025-11-20T09:53:53.988713-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.988734-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007a7d0 sp=0x400007a7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.988761-07:00 granite ollama[32079]: created by runtime.createfing in goroutine 1
- 2025-11-20T09:53:53.988803-07:00 granite ollama[32079]: #011runtime/mfinal.go:166 +0x80
- 2025-11-20T09:53:53.988826-07:00 granite ollama[32079]: goroutine 6 gp=0x40001ec700 m=nil [chan receive]:
- 2025-11-20T09:53:53.988857-07:00 granite ollama[32079]: runtime.gopark(0x4000183ae0?, 0x4002464018?, 0x48?, 0xc7?, 0xaaaad08c5c18?)
- 2025-11-20T09:53:53.988886-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007c6f0 sp=0x400007c6d0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.988912-07:00 granite ollama[32079]: runtime.chanrecv(0x4000036380, 0x0, 0x1)
- 2025-11-20T09:53:53.988944-07:00 granite ollama[32079]: #011runtime/chan.go:664 +0x42c fp=0x400007c770 sp=0x400007c6f0 pc=0xaaaad0794bec
- 2025-11-20T09:53:53.988966-07:00 granite ollama[32079]: runtime.chanrecv1(0x0?, 0x0?)
- 2025-11-20T09:53:53.988989-07:00 granite ollama[32079]: #011runtime/chan.go:506 +0x14 fp=0x400007c7a0 sp=0x400007c770 pc=0xaaaad0794784
- 2025-11-20T09:53:53.989016-07:00 granite ollama[32079]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
- 2025-11-20T09:53:53.989039-07:00 granite ollama[32079]: #011runtime/mgc.go:1796
- 2025-11-20T09:53:53.989061-07:00 granite ollama[32079]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
- 2025-11-20T09:53:53.989084-07:00 granite ollama[32079]: #011runtime/mgc.go:1799 +0x3c fp=0x400007c7d0 sp=0x400007c7a0 pc=0xaaaad07a6dac
- 2025-11-20T09:53:53.989107-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.989130-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007c7d0 sp=0x400007c7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.989157-07:00 granite ollama[32079]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
- 2025-11-20T09:53:53.989184-07:00 granite ollama[32079]: #011runtime/mgc.go:1794 +0x78
- 2025-11-20T09:53:53.989207-07:00 granite ollama[32079]: goroutine 7 gp=0x40001ece00 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.989235-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.989263-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007cf10 sp=0x400007cef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.989291-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.989322-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400007cfb0 sp=0x400007cf10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.989345-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.989374-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400007cfd0 sp=0x400007cfb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.989396-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.989418-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007cfd0 sp=0x400007cfd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.989445-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.989467-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.989491-07:00 granite ollama[32079]: goroutine 18 gp=0x4000102380 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.989517-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.989664-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000076710 sp=0x40000766f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.989689-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.989713-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x40000767b0 sp=0x4000076710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.989738-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.989762-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x40000767d0 sp=0x40000767b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.989796-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.989821-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x40000767d0 sp=0x40000767d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.989854-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.989878-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.989902-07:00 granite ollama[32079]: goroutine 34 gp=0x4000504000 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.989933-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.989957-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400050a710 sp=0x400050a6f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.989990-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.990014-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400050a7b0 sp=0x400050a710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.990038-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.990062-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400050a7d0 sp=0x400050a7b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.990086-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.990110-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400050a7d0 sp=0x400050a7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.990134-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.990157-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.990181-07:00 granite ollama[32079]: goroutine 8 gp=0x40001ecfc0 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.990205-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.990228-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007d710 sp=0x400007d6f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.990252-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.990277-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400007d7b0 sp=0x400007d710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.990301-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.990324-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400007d7d0 sp=0x400007d7b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.990359-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.990382-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007d7d0 sp=0x400007d7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.990407-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.990430-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.990454-07:00 granite ollama[32079]: goroutine 19 gp=0x4000102540 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.990486-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.990510-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000076f10 sp=0x4000076ef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.990534-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.990558-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x4000076fb0 sp=0x4000076f10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.990582-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.990718-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x4000076fd0 sp=0x4000076fb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.990743-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.990767-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x4000076fd0 sp=0x4000076fd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.990795-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.990818-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.990842-07:00 granite ollama[32079]: goroutine 35 gp=0x40005041c0 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.990872-07:00 granite ollama[32079]: runtime.gopark(0x3dc40be43e95?, 0x0?, 0x0?, 0x0?, 0x0?)
- 2025-11-20T09:53:53.990901-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400050af10 sp=0x400050aef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.990929-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.990953-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400050afb0 sp=0x400050af10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.990978-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.991002-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400050afd0 sp=0x400050afb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.991029-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.991053-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400050afd0 sp=0x400050afd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.991077-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.991101-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.991125-07:00 granite ollama[32079]: goroutine 9 gp=0x40001ed180 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.991155-07:00 granite ollama[32079]: runtime.gopark(0xaaaad2456240?, 0x1?, 0xd9?, 0x47?, 0x0?)
- 2025-11-20T09:53:53.991180-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400007df10 sp=0x400007def0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.991205-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.991229-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400007dfb0 sp=0x400007df10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.991260-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.991284-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400007dfd0 sp=0x400007dfb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.991309-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.991333-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400007dfd0 sp=0x400007dfd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.991358-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.991385-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.991410-07:00 granite ollama[32079]: goroutine 20 gp=0x4000102700 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.991434-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af45a7d?, 0x3?, 0x78?, 0xf4?, 0x0?)
- 2025-11-20T09:53:53.991459-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000077710 sp=0x40000776f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.991492-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.991517-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x40000777b0 sp=0x4000077710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.991545-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.991569-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x40000777d0 sp=0x40000777b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.991594-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.991618-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x40000777d0 sp=0x40000777d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.991642-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.991786-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.991810-07:00 granite ollama[32079]: goroutine 36 gp=0x4000504380 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.991847-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af7e4d9?, 0x1?, 0xd7?, 0xa8?, 0x0?)
- 2025-11-20T09:53:53.991872-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400050b710 sp=0x400050b6f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.991896-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.991920-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400050b7b0 sp=0x400050b710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.991948-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.991976-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400050b7d0 sp=0x400050b7b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.992000-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.992024-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400050b7d0 sp=0x400050b7d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.992048-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.992072-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.992096-07:00 granite ollama[32079]: goroutine 10 gp=0x40001ed340 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.992125-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af7db7b?, 0x1?, 0x26?, 0x22?, 0x0?)
- 2025-11-20T09:53:53.992149-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000506710 sp=0x40005066f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.992178-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.992202-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x40005067b0 sp=0x4000506710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.992226-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.992249-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x40005067d0 sp=0x40005067b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.992276-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.992300-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x40005067d0 sp=0x40005067d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.992328-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.992351-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.992375-07:00 granite ollama[32079]: goroutine 21 gp=0x40001028c0 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.992403-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af493ed?, 0x1?, 0xfd?, 0xd6?, 0x0?)
- 2025-11-20T09:53:53.992436-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000077f10 sp=0x4000077ef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.992467-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.992496-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x4000077fb0 sp=0x4000077f10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.992524-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.992547-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x4000077fd0 sp=0x4000077fb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.992571-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.992595-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x4000077fd0 sp=0x4000077fd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.992619-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.992643-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.992668-07:00 granite ollama[32079]: goroutine 37 gp=0x4000504540 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.992696-07:00 granite ollama[32079]: runtime.gopark(0x3dc40be3304b?, 0x1?, 0x59?, 0xcf?, 0x0?)
- 2025-11-20T09:53:53.992721-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400050bf10 sp=0x400050bef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.992868-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.992892-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x400050bfb0 sp=0x400050bf10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.992916-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.992940-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x400050bfd0 sp=0x400050bfb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.992964-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.992988-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400050bfd0 sp=0x400050bfd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.993018-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.993042-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.993065-07:00 granite ollama[32079]: goroutine 11 gp=0x40001ed500 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.993090-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af47b1d?, 0x1?, 0xbb?, 0x34?, 0x0?)
- 2025-11-20T09:53:53.993114-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000506f10 sp=0x4000506ef0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.993139-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.993163-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x4000506fb0 sp=0x4000506f10 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.993187-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.993210-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x4000506fd0 sp=0x4000506fb0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.993233-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.993258-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x4000506fd0 sp=0x4000506fd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.993286-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.993309-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.993333-07:00 granite ollama[32079]: goroutine 22 gp=0x4000102a80 m=nil [GC worker (idle)]:
- 2025-11-20T09:53:53.993367-07:00 granite ollama[32079]: runtime.gopark(0x3dc40af4548f?, 0x3?, 0xca?, 0x57?, 0x0?)
- 2025-11-20T09:53:53.993392-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000078710 sp=0x40000786f0 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.993417-07:00 granite ollama[32079]: runtime.gcBgMarkWorker(0x4000037960)
- 2025-11-20T09:53:53.993440-07:00 granite ollama[32079]: #011runtime/mgc.go:1423 +0xdc fp=0x40000787b0 sp=0x4000078710 pc=0xaaaad07a601c
- 2025-11-20T09:53:53.993468-07:00 granite ollama[32079]: runtime.gcBgMarkStartWorkers.gowrap1()
- 2025-11-20T09:53:53.993491-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x28 fp=0x40000787d0 sp=0x40000787b0 pc=0xaaaad07a5f08
- 2025-11-20T09:53:53.993515-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.993537-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x40000787d0 sp=0x40000787d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.993560-07:00 granite ollama[32079]: created by runtime.gcBgMarkStartWorkers in goroutine 1
- 2025-11-20T09:53:53.993581-07:00 granite ollama[32079]: #011runtime/mgc.go:1339 +0x140
- 2025-11-20T09:53:53.993604-07:00 granite ollama[32079]: goroutine 12 gp=0x4000505340 m=nil [sync.WaitGroup.Wait]:
- 2025-11-20T09:53:53.993632-07:00 granite ollama[32079]: runtime.gopark(0xaaaad23b4600?, 0x0?, 0x0?, 0xa0?, 0x0?)
- 2025-11-20T09:53:53.993660-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x400008da90 sp=0x400008da70 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.993684-07:00 granite ollama[32079]: runtime.goparkunlock(...)
- 2025-11-20T09:53:53.993707-07:00 granite ollama[32079]: #011runtime/proc.go:441
- 2025-11-20T09:53:53.993730-07:00 granite ollama[32079]: runtime.semacquire1(0x4000234bf8, 0x0, 0x1, 0x0, 0x18)
- 2025-11-20T09:53:53.993755-07:00 granite ollama[32079]: #011runtime/sema.go:188 +0x204 fp=0x400008dae0 sp=0x400008da90 pc=0xaaaad07d9674
- 2025-11-20T09:53:53.993779-07:00 granite ollama[32079]: sync.runtime_SemacquireWaitGroup(0x0?)
- 2025-11-20T09:53:53.994169-07:00 granite ollama[32079]: #011runtime/sema.go:110 +0x2c fp=0x400008db20 sp=0x400008dae0 pc=0xaaaad07fa81c
- 2025-11-20T09:53:53.994194-07:00 granite ollama[32079]: sync.(*WaitGroup).Wait(0x4000234bf0)
- 2025-11-20T09:53:53.994224-07:00 granite ollama[32079]: #011sync/waitgroup.go:118 +0x70 fp=0x400008db40 sp=0x400008db20 pc=0xaaaad080c310
- 2025-11-20T09:53:53.994254-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x4000234b40, {0xaaaad1b2bf00, 0x400037c410})
- 2025-11-20T09:53:53.994280-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:441 +0x38 fp=0x400008dfa0 sp=0x400008db40 pc=0xaaaad0c799c8
- 2025-11-20T09:53:53.994305-07:00 granite ollama[32079]: github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
- 2025-11-20T09:53:53.994333-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1411 +0x30 fp=0x400008dfd0 sp=0x400008dfa0 pc=0xaaaad0c816a0
- 2025-11-20T09:53:53.994358-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.994381-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x400008dfd0 sp=0x400008dfd0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.994405-07:00 granite ollama[32079]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
- 2025-11-20T09:53:53.994429-07:00 granite ollama[32079]: #011github.com/ollama/ollama/runner/ollamarunner/runner.go:1411 +0x448
- 2025-11-20T09:53:53.994453-07:00 granite ollama[32079]: goroutine 38 gp=0x40005056c0 m=nil [IO wait]:
- 2025-11-20T09:53:53.994478-07:00 granite ollama[32079]: runtime.gopark(0x0?, 0x0?, 0xc8?, 0x85?, 0xaaaad0799230?)
- 2025-11-20T09:53:53.994502-07:00 granite ollama[32079]: #011runtime/proc.go:435 +0xc8 fp=0x4000508580 sp=0x4000508560 pc=0xaaaad07f8e68
- 2025-11-20T09:53:53.994526-07:00 granite ollama[32079]: runtime.netpollblock(0x0?, 0xffffffff?, 0xff?)
- 2025-11-20T09:53:53.994559-07:00 granite ollama[32079]: #011runtime/netpoll.go:575 +0x158 fp=0x40005085c0 sp=0x4000508580 pc=0xaaaad07bde28
- 2025-11-20T09:53:53.994584-07:00 granite ollama[32079]: internal/poll.runtime_pollWait(0xffffa1c86e18, 0x72)
- 2025-11-20T09:53:53.994614-07:00 granite ollama[32079]: #011runtime/netpoll.go:351 +0xa0 fp=0x40005085f0 sp=0x40005085c0 pc=0xaaaad07f8020
- 2025-11-20T09:53:53.994642-07:00 granite ollama[32079]: internal/poll.(*pollDesc).wait(0x4000490280?, 0x4000686a31?, 0x0)
- 2025-11-20T09:53:53.994667-07:00 granite ollama[32079]: #011internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x4000508620 sp=0x40005085f0 pc=0xaaaad087a3f8
- 2025-11-20T09:53:53.994693-07:00 granite ollama[32079]: internal/poll.(*pollDesc).waitRead(...)
- 2025-11-20T09:53:53.994717-07:00 granite ollama[32079]: #011internal/poll/fd_poll_runtime.go:89
- 2025-11-20T09:53:53.994741-07:00 granite ollama[32079]: internal/poll.(*FD).Read(0x4000490280, {0x4000686a31, 0x1, 0x1})
- 2025-11-20T09:53:53.994768-07:00 granite ollama[32079]: #011internal/poll/fd_unix.go:165 +0x1fc fp=0x40005086c0 sp=0x4000508620 pc=0xaaaad087b6ac
- 2025-11-20T09:53:53.994792-07:00 granite ollama[32079]: net.(*netFD).Read(0x4000490280, {0x4000686a31?, 0x4000508758?, 0xaaaad0aaa784?})
- 2025-11-20T09:53:53.994822-07:00 granite ollama[32079]: #011net/fd_posix.go:55 +0x28 fp=0x4000508710 sp=0x40005086c0 pc=0xaaaad08ebc28
- 2025-11-20T09:53:53.994847-07:00 granite ollama[32079]: net.(*conn).Read(0x400052e4f8, {0x4000686a31?, 0x0?, 0x0?})
- 2025-11-20T09:53:53.994875-07:00 granite ollama[32079]: #011net/net.go:194 +0x34 fp=0x4000508760 sp=0x4000508710 pc=0xaaaad08f9364
- 2025-11-20T09:53:53.994900-07:00 granite ollama[32079]: net/http.(*connReader).backgroundRead(0x4000686a20)
- 2025-11-20T09:53:53.994991-07:00 granite ollama[32079]: #011net/http/server.go:690 +0x40 fp=0x40005087b0 sp=0x4000508760 pc=0xaaaad0aaa680
- 2025-11-20T09:53:53.995016-07:00 granite ollama[32079]: net/http.(*connReader).startBackgroundRead.gowrap2()
- 2025-11-20T09:53:53.995048-07:00 granite ollama[32079]: #011net/http/server.go:686 +0x28 fp=0x40005087d0 sp=0x40005087b0 pc=0xaaaad0aaa568
- 2025-11-20T09:53:53.995072-07:00 granite ollama[32079]: runtime.goexit({})
- 2025-11-20T09:53:53.995096-07:00 granite ollama[32079]: #011runtime/asm_arm64.s:1223 +0x4 fp=0x40005087d0 sp=0x40005087d0 pc=0xaaaad0800d54
- 2025-11-20T09:53:53.995125-07:00 granite ollama[32079]: created by net/http.(*connReader).startBackgroundRead in goroutine 13
- 2025-11-20T09:53:53.995155-07:00 granite ollama[32079]: #011net/http/server.go:686 +0xc4
- 2025-11-20T09:53:53.995180-07:00 granite ollama[32079]: r0 0x0
- 2025-11-20T09:53:53.995203-07:00 granite ollama[32079]: r1 0x7dae
- 2025-11-20T09:53:53.995227-07:00 granite ollama[32079]: r2 0x6
- 2025-11-20T09:53:53.995251-07:00 granite ollama[32079]: r3 0xffff517af140
- 2025-11-20T09:53:53.995275-07:00 granite ollama[32079]: r4 0xffffa248bb50
- 2025-11-20T09:53:53.995299-07:00 granite ollama[32079]: r5 0x1
- 2025-11-20T09:53:53.995326-07:00 granite ollama[32079]: r6 0x20
- 2025-11-20T09:53:53.995350-07:00 granite ollama[32079]: r7 0xffff517adcb0
- 2025-11-20T09:53:53.995377-07:00 granite ollama[32079]: r8 0x83
- 2025-11-20T09:53:53.995404-07:00 granite ollama[32079]: r9 0x0
- 2025-11-20T09:53:53.995428-07:00 granite ollama[32079]: r10 0xa
- 2025-11-20T09:53:53.995451-07:00 granite ollama[32079]: r11 0x101010101010101
- 2025-11-20T09:53:53.995475-07:00 granite ollama[32079]: r12 0xffff517add40
- 2025-11-20T09:53:53.995502-07:00 granite ollama[32079]: r13 0x0
- 2025-11-20T09:53:53.995525-07:00 granite ollama[32079]: r14 0x0
- 2025-11-20T09:53:53.995548-07:00 granite ollama[32079]: r15 0x51eb851eb851eb0
- 2025-11-20T09:53:53.995572-07:00 granite ollama[32079]: r16 0x1
- 2025-11-20T09:53:53.995595-07:00 granite ollama[32079]: r17 0xffffa1e57d0c
- 2025-11-20T09:53:53.995619-07:00 granite ollama[32079]: r18 0xfffebd41e4f4
- 2025-11-20T09:53:53.995654-07:00 granite ollama[32079]: r19 0x7dae
- 2025-11-20T09:53:53.995688-07:00 granite ollama[32079]: r20 0xffff517af140
- 2025-11-20T09:53:53.995712-07:00 granite ollama[32079]: r21 0x6
- 2025-11-20T09:53:53.995739-07:00 granite ollama[32079]: r22 0xffff23fef000
- 2025-11-20T09:53:53.995762-07:00 granite ollama[32079]: r23 0x0
- 2025-11-20T09:53:53.995789-07:00 granite ollama[32079]: r24 0xffff387875f8
- 2025-11-20T09:53:53.995814-07:00 granite ollama[32079]: r25 0x400004d7a8
- 2025-11-20T09:53:53.995838-07:00 granite ollama[32079]: r26 0xaaaad1b157e0
- 2025-11-20T09:53:53.995862-07:00 granite ollama[32079]: r27 0x10
- 2025-11-20T09:53:53.995886-07:00 granite ollama[32079]: r28 0x4000602540
- 2025-11-20T09:53:53.995915-07:00 granite ollama[32079]: r29 0xffff517adc40
- 2025-11-20T09:53:53.995944-07:00 granite ollama[32079]: lr 0xffffa1eb75f4
- 2025-11-20T09:53:53.995968-07:00 granite ollama[32079]: sp 0xffff517adc30
- 2025-11-20T09:53:53.995992-07:00 granite ollama[32079]: pc 0xffffa1eb7608
- 2025-11-20T09:53:53.996016-07:00 granite ollama[32079]: fault 0x0
- 2025-11-20T09:53:54.025053-07:00 granite ollama[32079]: time=2025-11-20T09:53:54.024-07:00 level=INFO source=sched.go:470 msg="Load failed" model=/usr/share/ollama/.ollama/models/blobs/sha256-90a618fe6ff21b09ca968df959104eb650658b0bef0faef785c18c2795d993e3 error="do load request: Post \"http://127.0.0.1:41093/load\": EOF"
- 2025-11-20T09:53:54.025091-07:00 granite ollama[32079]: time=2025-11-20T09:53:54.025-07:00 level=DEBUG source=server.go:1755 msg="stopping llama server" pid=32160
- 2025-11-20T09:53:54.025125-07:00 granite ollama[32079]: time=2025-11-20T09:53:54.025-07:00 level=DEBUG source=server.go:1761 msg="waiting for llama server to exit" pid=32160
- 2025-11-20T09:53:54.072816-07:00 granite ollama[32079]: time=2025-11-20T09:53:54.072-07:00 level=ERROR source=server.go:265 msg="llama runner terminated" error="exit status 2"
- 2025-11-20T09:53:54.072933-07:00 granite ollama[32079]: time=2025-11-20T09:53:54.072-07:00 level=DEBUG source=server.go:1765 msg="llama server stopped" pid=32160
- 2025-11-20T09:53:54.072979-07:00 granite ollama[32079]: [GIN] 2025/11/20 - 09:53:54 | 500 | 2.036045869s | 127.0.0.1 | POST "/api/generate"
Advertisement
Add Comment
Please, Sign In to add comment