github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 13:11:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13325] GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed #34561

New Issue
Closed
opened 2026-04-22 18:15:13 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 18:15:13 -05:00
Owner
Copy Link

Originally created by @benmishkanian on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13325

What is the issue?

I am trying to run this:
ollama run gpt-oss:20b
and I get error:
Error: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed

I am noticing that when ollama updates, I have no problems running this command once. But then the second time and all subsequent times, I get this error. I don't have this problem with other models besides gpt-oss.

Relevant log output

time=2025-12-03T21:10:01.882-08:00 level=INFO source=routes.go:1304 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:8192 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false 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:C:\\Users\\Fusio\\.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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-12-03T21:10:01.885-08:00 level=INFO source=images.go:477 msg="total blobs: 26"
time=2025-12-03T21:10:01.886-08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
time=2025-12-03T21:10:01.887-08:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version ${PKG_VERSION})"
time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=sched.go:106 msg="starting llm scheduler"
time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=24 efficiency=16 threads=32
time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA"
time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvml.dll
time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Scripts\\nvml.dll C:\\Users\\Fusio\\miniforge3\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\condabin\\nvml.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64\\nvml.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\nvml.dll C:\\Program Files\\Oculus\\Support\\oculus-runtime\\nvml.dll C:\\Windows\\system32\\nvml.dll C:\\Windows\\nvml.dll C:\\Windows\\System32\\Wbem\\nvml.dll C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\Windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll F:\\jdk-21.0.2\\bin\\nvml.dll C:\\Program Files\\dotnet\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll C:\\WINDOWS\\nvml.dll C:\\WINDOWS\\System32\\Wbem\\nvml.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\WINDOWS\\System32\\OpenSSH\\nvml.dll C:\\Program Files\\GitHub CLI\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0\\nvml.dll F:\\Programs\\Godot\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\Fusio\\Projects\\TempoTactics\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama\\nvml.dll C:\\Users\\Fusio\\.dotnet\\tools\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-12-03T21:10:01.888-08:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll"
time=2025-12-03T21:10:01.888-08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\Windows\\system32\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll c:\\Windows\\System32\\nvml.dll]"
time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:111 msg="nvidia-ml loaded" library=C:\Windows\system32\nvml.dll
time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvcuda.dll
time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Scripts\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\condabin\\nvcuda.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64\\nvcuda.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\nvcuda.dll C:\\Program Files\\Oculus\\Support\\oculus-runtime\\nvcuda.dll C:\\Windows\\system32\\nvcuda.dll C:\\Windows\\nvcuda.dll C:\\Windows\\System32\\Wbem\\nvcuda.dll C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\Windows\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll F:\\jdk-21.0.2\\bin\\nvcuda.dll C:\\Program Files\\dotnet\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll C:\\WINDOWS\\nvcuda.dll C:\\WINDOWS\\System32\\Wbem\\nvcuda.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\WINDOWS\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files\\GitHub CLI\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0\\nvcuda.dll F:\\Programs\\Godot\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\Fusio\\Projects\\TempoTactics\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama\\nvcuda.dll C:\\Users\\Fusio\\.dotnet\\tools\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]"
time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll"
time=2025-12-03T21:10:01.901-08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\Windows\\system32\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll]"
initializing C:\Windows\system32\nvcuda.dll
dlsym: cuInit - 00007FF95A98DE10
dlsym: cuDriverGetVersion - 00007FF95A98DEB0
dlsym: cuDeviceGetCount - 00007FF95A98E6A6
dlsym: cuDeviceGet - 00007FF95A98E6A0
dlsym: cuDeviceGetAttribute - 00007FF95A98E000
dlsym: cuDeviceGetUuid - 00007FF95A98E6B2
dlsym: cuDeviceGetName - 00007FF95A98E6AC
dlsym: cuCtxCreate_v3 - 00007FF95A98E72A
dlsym: cuMemGetInfo_v2 - 00007FF95A98E82C
dlsym: cuCtxDestroy - 00007FF95A98E73C
calling cuInit
calling cuDriverGetVersion
raw version 0x32c8
CUDA driver version: 13.0
calling cuDeviceGetCount
device count 1
time=2025-12-03T21:10:01.910-08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=C:\Windows\system32\nvcuda.dll
[GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] CUDA totalMem 24563mb
[GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] CUDA freeMem 22992mb
[GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] Compute Capability 8.9
time=2025-12-03T21:10:02.095-08:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found."
releasing cuda driver library
releasing nvml library
time=2025-12-03T21:10:02.096-08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 library=cuda variant=v12 compute=8.9 driver=13.0 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="22.5 GiB"
[GIN] 2025/12/03 - 21:10:02 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/12/03 - 21:10:02 | 200 |     40.0379ms |       127.0.0.1 | GET      "/api/tags"
time=2025-12-03T21:10:02.155-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/12/03 - 21:10:02 | 200 |     61.0791ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/12/03 - 21:10:10 | 200 |       511.1µs |       127.0.0.1 | HEAD     "/"
time=2025-12-03T21:10:10.578-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/12/03 - 21:10:10 | 200 |       60.63ms |       127.0.0.1 | POST     "/api/show"
time=2025-12-03T21:10:10.616-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="27.7 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:10.633-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.5 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:10.634-08:00 level=DEBUG source=sched.go:183 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2025-12-03T21:10:10.650-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=sched.go:226 msg="loading first model" model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[22.1 GiB]"
time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gptoss.vision.block_count default=0
time=2025-12-03T21:10:10.685-08:00 level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 parallel=1 available=23776518144 required="5.1 GiB"
time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:10.709-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:10.710-08:00 level=INFO source=server.go:135 msg="system memory" total="31.7 GiB" free="15.7 GiB" free_swap="28.0 GiB"
time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[22.1 GiB]"
time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gptoss.vision.block_count default=0
time=2025-12-03T21:10:10.710-08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[22.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="5.1 GiB" memory.required.kv="300.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="2.0 GiB" memory.graph.partial="2.0 GiB"
time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=server.go:291 msg="compatible gpu libraries" compatible=[]
time=2025-12-03T21:10:10.738-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
time=2025-12-03T21:10:10.738-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=tokenizer.ggml.pretokenizer default="[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]*[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
time=2025-12-03T21:10:10.743-08:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\Users\\Fusio\\miniforge3\\Library\\bin\\ollama.exe runner --ollama-engine --model C:\\Users\\Fusio\\.ollama\\models\\blobs\\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --ctx-size 8192 --batch-size 512 --n-gpu-layers 25 --threads 8 --no-mmap --parallel 1 --port 56821"
time=2025-12-03T21:10:10.743-08:00 level=DEBUG source=server.go:439 msg=subprocess OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_DEBUG=1 OLLAMA_MODELS=C:\Users\Fusio\.ollama\models CUDA_PATH_V13_0="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0" PATH="C:\\Users\\Fusio\\miniforge3\\Library\\bin;C:\\Users\\Fusio\\miniforge3;C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\bin;C:\\Users\\Fusio\\miniforge3\\Scripts;C:\\Users\\Fusio\\miniforge3\\bin;C:\\Users\\Fusio\\miniforge3\\condabin;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin;C:\\Program Files\\Oculus\\Support\\oculus-runtime;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0;C:\\Windows\\System32\\OpenSSH;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Git\\cmd;F:\\jdk-21.0.2\\bin;C:\\Program Files\\dotnet;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0;C:\\WINDOWS\\System32\\OpenSSH;C:\\Program Files\\GitHub CLI;C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0;F:\\Programs\\Godot;C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps;.;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Fusio\\.dotnet\\tools;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\bin" OLLAMA_CONTEXT_LENGTH=8192 CUDA_PATH="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0" OLLAMA_LIBRARY_PATH=C:\Users\Fusio\miniforge3\Library\bin CUDA_VISIBLE_DEVICES=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2
time=2025-12-03T21:10:10.745-08:00 level=INFO source=sched.go:481 msg="loaded runners" count=1
time=2025-12-03T21:10:10.745-08:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-12-03T21:10:10.747-08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error"
time=2025-12-03T21:10:10.774-08:00 level=INFO source=runner.go:925 msg="starting ollama engine"
time=2025-12-03T21:10:10.775-08:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:56821"
time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32
time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.name default=""
time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.description default=""
time=2025-12-03T21:10:10.804-08:00 level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32
time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Fusio\miniforge3\Library\bin
time=2025-12-03T21:10:10.830-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
ggml.c:1542: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed
time=2025-12-03T21:10:11.198-08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-12-03T21:10:11.342-08:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 0xc0000409"
time=2025-12-03T21:10:11.448-08:00 level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed"
time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:489 msg="triggering expiration for failed load" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
[GIN] 2025/12/03 - 21:10:11 | 500 |    867.5959ms |       127.0.0.1 | POST     "/api/generate"
time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:362 msg="runner expired event received" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:377 msg="got lock to unload expired event" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:400 msg="starting background wait for VRAM recovery" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
time=2025-12-03T21:10:11.449-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:11.468-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:11.470-08:00 level=DEBUG source=server.go:1031 msg="stopping llama server" pid=58164
time=2025-12-03T21:10:11.470-08:00 level=DEBUG source=sched.go:405 msg="runner terminated and removed from list, blocking for VRAM recovery" runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2025-12-03T21:10:11.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:11.732-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:11.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:11.997-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:12.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:12.245-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:12.471-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:12.493-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:12.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:12.736-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:12.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:12.985-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:13.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:13.234-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:13.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:13.483-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:13.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:13.746-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:13.971-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:13.992-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:14.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:14.240-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:14.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:14.489-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:14.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:14.736-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:14.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:14.982-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:15.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:15.246-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:15.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:15.493-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:15.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:15.742-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:15.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:15.992-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:16.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:16.239-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:16.470-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0209205 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=sched.go:408 msg="sending an unloaded event" runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=sched.go:310 msg="ignoring unload event with no pending requests"
time=2025-12-03T21:10:16.488-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:16.720-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.271178 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2025-12-03T21:10:16.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB"
time=2025-12-03T21:10:16.735-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB"
releasing nvml library
time=2025-12-03T21:10:16.971-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5215057 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
[GIN] 2025/12/03 - 21:10:32 | 200 |      4.3786ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/12/03 - 21:11:02 | 200 |      3.7647ms |       127.0.0.1 | GET      "/api/tags"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

ollama version is ${PKG_VERSION}

Originally created by @benmishkanian on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13325 ### What is the issue? I am trying to run this: `ollama run gpt-oss:20b` and I get error: `Error: 500 Internal Server Error: llama runner process has terminated: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed` I am noticing that when ollama updates, I have no problems running this command once. But then the second time and all subsequent times, I get this error. I don't have this problem with other models besides gpt-oss. ### Relevant log output ```shell time=2025-12-03T21:10:01.882-08:00 level=INFO source=routes.go:1304 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:8192 OLLAMA_DEBUG:DEBUG OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false 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:C:\\Users\\Fusio\\.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_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-12-03T21:10:01.885-08:00 level=INFO source=images.go:477 msg="total blobs: 26" time=2025-12-03T21:10:01.886-08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" time=2025-12-03T21:10:01.887-08:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version ${PKG_VERSION})" time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=sched.go:106 msg="starting llm scheduler" time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-12-03T21:10:01.887-08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=24 efficiency=16 threads=32 time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:98 msg="searching for GPU discovery libraries for NVIDIA" time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvml.dll time=2025-12-03T21:10:01.887-08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\Scripts\\nvml.dll C:\\Users\\Fusio\\miniforge3\\bin\\nvml.dll C:\\Users\\Fusio\\miniforge3\\condabin\\nvml.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64\\nvml.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\nvml.dll C:\\Program Files\\Oculus\\Support\\oculus-runtime\\nvml.dll C:\\Windows\\system32\\nvml.dll C:\\Windows\\nvml.dll C:\\Windows\\System32\\Wbem\\nvml.dll C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\Windows\\System32\\OpenSSH\\nvml.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll C:\\Program Files\\Git\\cmd\\nvml.dll F:\\jdk-21.0.2\\bin\\nvml.dll C:\\Program Files\\dotnet\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll C:\\WINDOWS\\nvml.dll C:\\WINDOWS\\System32\\Wbem\\nvml.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvml.dll C:\\WINDOWS\\System32\\OpenSSH\\nvml.dll C:\\Program Files\\GitHub CLI\\nvml.dll C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0\\nvml.dll F:\\Programs\\Godot\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps\\nvml.dll C:\\Users\\Fusio\\Projects\\TempoTactics\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama\\nvml.dll C:\\Users\\Fusio\\.dotnet\\tools\\nvml.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-12-03T21:10:01.888-08:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvml.dll" time=2025-12-03T21:10:01.888-08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\Windows\\system32\\nvml.dll C:\\WINDOWS\\system32\\nvml.dll c:\\Windows\\System32\\nvml.dll]" time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:111 msg="nvidia-ml loaded" library=C:\Windows\system32\nvml.dll time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:501 msg="Searching for GPU library" name=nvcuda.dll time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:525 msg="gpu library search" globs="[C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Library\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\Scripts\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\bin\\nvcuda.dll C:\\Users\\Fusio\\miniforge3\\condabin\\nvcuda.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64\\nvcuda.dll C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\nvcuda.dll C:\\Program Files\\Oculus\\Support\\oculus-runtime\\nvcuda.dll C:\\Windows\\system32\\nvcuda.dll C:\\Windows\\nvcuda.dll C:\\Windows\\System32\\Wbem\\nvcuda.dll C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\Windows\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll C:\\Program Files\\Git\\cmd\\nvcuda.dll F:\\jdk-21.0.2\\bin\\nvcuda.dll C:\\Program Files\\dotnet\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll C:\\WINDOWS\\nvcuda.dll C:\\WINDOWS\\System32\\Wbem\\nvcuda.dll C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\nvcuda.dll C:\\WINDOWS\\System32\\OpenSSH\\nvcuda.dll C:\\Program Files\\GitHub CLI\\nvcuda.dll C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0\\nvcuda.dll F:\\Programs\\Godot\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps\\nvcuda.dll C:\\Users\\Fusio\\Projects\\TempoTactics\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama\\nvcuda.dll C:\\Users\\Fusio\\.dotnet\\tools\\nvcuda.dll C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin\\nvcuda.dll c:\\windows\\system*\\nvcuda.dll]" time=2025-12-03T21:10:01.900-08:00 level=DEBUG source=gpu.go:529 msg="skipping PhysX cuda library path" path="C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common\\nvcuda.dll" time=2025-12-03T21:10:01.901-08:00 level=DEBUG source=gpu.go:558 msg="discovered GPU libraries" paths="[C:\\Windows\\system32\\nvcuda.dll C:\\WINDOWS\\system32\\nvcuda.dll]" initializing C:\Windows\system32\nvcuda.dll dlsym: cuInit - 00007FF95A98DE10 dlsym: cuDriverGetVersion - 00007FF95A98DEB0 dlsym: cuDeviceGetCount - 00007FF95A98E6A6 dlsym: cuDeviceGet - 00007FF95A98E6A0 dlsym: cuDeviceGetAttribute - 00007FF95A98E000 dlsym: cuDeviceGetUuid - 00007FF95A98E6B2 dlsym: cuDeviceGetName - 00007FF95A98E6AC dlsym: cuCtxCreate_v3 - 00007FF95A98E72A dlsym: cuMemGetInfo_v2 - 00007FF95A98E82C dlsym: cuCtxDestroy - 00007FF95A98E73C calling cuInit calling cuDriverGetVersion raw version 0x32c8 CUDA driver version: 13.0 calling cuDeviceGetCount device count 1 time=2025-12-03T21:10:01.910-08:00 level=DEBUG source=gpu.go:125 msg="detected GPUs" count=1 library=C:\Windows\system32\nvcuda.dll [GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] CUDA totalMem 24563mb [GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] CUDA freeMem 22992mb [GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2] Compute Capability 8.9 time=2025-12-03T21:10:02.095-08:00 level=DEBUG source=amd_windows.go:34 msg="unable to load amdhip64_6.dll, please make sure to upgrade to the latest amd driver: The specified module could not be found." releasing cuda driver library releasing nvml library time=2025-12-03T21:10:02.096-08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 library=cuda variant=v12 compute=8.9 driver=13.0 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="22.5 GiB" [GIN] 2025/12/03 - 21:10:02 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/12/03 - 21:10:02 | 200 | 40.0379ms | 127.0.0.1 | GET "/api/tags" time=2025-12-03T21:10:02.155-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/12/03 - 21:10:02 | 200 | 61.0791ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/12/03 - 21:10:10 | 200 | 511.1µs | 127.0.0.1 | HEAD "/" time=2025-12-03T21:10:10.578-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/12/03 - 21:10:10 | 200 | 60.63ms | 127.0.0.1 | POST "/api/show" time=2025-12-03T21:10:10.616-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="27.7 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:10.633-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.5 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:10.634-08:00 level=DEBUG source=sched.go:183 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 time=2025-12-03T21:10:10.650-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=sched.go:226 msg="loading first model" model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[22.1 GiB]" time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gptoss.vision.block_count default=0 time=2025-12-03T21:10:10.685-08:00 level=INFO source=sched.go:786 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 parallel=1 available=23776518144 required="5.1 GiB" time=2025-12-03T21:10:10.685-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:10.709-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:10.710-08:00 level=INFO source=server.go:135 msg="system memory" total="31.7 GiB" free="15.7 GiB" free_swap="28.0 GiB" time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=memory.go:111 msg=evaluating library=cuda gpu_count=1 available="[22.1 GiB]" time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=gptoss.vision.block_count default=0 time=2025-12-03T21:10:10.710-08:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[22.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="5.1 GiB" memory.required.kv="300.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.2 GiB" memory.weights.nonrepeating="1.1 GiB" memory.graph.full="2.0 GiB" memory.graph.partial="2.0 GiB" time=2025-12-03T21:10:10.710-08:00 level=DEBUG source=server.go:291 msg="compatible gpu libraries" compatible=[] time=2025-12-03T21:10:10.738-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 time=2025-12-03T21:10:10.738-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=tokenizer.ggml.pretokenizer default="[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]*[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]+(?i:'s|'t|'re|'ve|'m|'ll|'d)?|[^\\r\\n\\p{L}\\p{N}]?[\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}\\p{M}]+[\\p{Ll}\\p{Lm}\\p{Lo}\\p{M}]*(?i:'s|'t|'re|'ve|'m|'ll|'d)?|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n/]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" time=2025-12-03T21:10:10.743-08:00 level=INFO source=server.go:438 msg="starting llama server" cmd="C:\\Users\\Fusio\\miniforge3\\Library\\bin\\ollama.exe runner --ollama-engine --model C:\\Users\\Fusio\\.ollama\\models\\blobs\\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --ctx-size 8192 --batch-size 512 --n-gpu-layers 25 --threads 8 --no-mmap --parallel 1 --port 56821" time=2025-12-03T21:10:10.743-08:00 level=DEBUG source=server.go:439 msg=subprocess OLLAMA_MAX_LOADED_MODELS=3 OLLAMA_DEBUG=1 OLLAMA_MODELS=C:\Users\Fusio\.ollama\models CUDA_PATH_V13_0="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0" PATH="C:\\Users\\Fusio\\miniforge3\\Library\\bin;C:\\Users\\Fusio\\miniforge3;C:\\Users\\Fusio\\miniforge3\\Library\\mingw-w64\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\usr\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\bin;C:\\Users\\Fusio\\miniforge3\\Scripts;C:\\Users\\Fusio\\miniforge3\\bin;C:\\Users\\Fusio\\miniforge3\\condabin;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin\\x64;C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0\\bin;C:\\Program Files\\Oculus\\Support\\oculus-runtime;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0;C:\\Windows\\System32\\OpenSSH;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\Git\\cmd;F:\\jdk-21.0.2\\bin;C:\\Program Files\\dotnet;C:\\Program Files\\NVIDIA Corporation\\NVIDIA app\\NvDLISR;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0;C:\\WINDOWS\\System32\\OpenSSH;C:\\Program Files\\GitHub CLI;C:\\Program Files\\NVIDIA Corporation\\Nsight Compute 2025.3.0;F:\\Programs\\Godot;C:\\Users\\Fusio\\AppData\\Local\\Microsoft\\WindowsApps;.;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Fusio\\.dotnet\\tools;C:\\Users\\Fusio\\AppData\\Local\\Programs\\Kiro\\bin;C:\\Users\\Fusio\\miniforge3\\Library\\bin" OLLAMA_CONTEXT_LENGTH=8192 CUDA_PATH="C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v13.0" OLLAMA_LIBRARY_PATH=C:\Users\Fusio\miniforge3\Library\bin CUDA_VISIBLE_DEVICES=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 time=2025-12-03T21:10:10.745-08:00 level=INFO source=sched.go:481 msg="loaded runners" count=1 time=2025-12-03T21:10:10.745-08:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-12-03T21:10:10.747-08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server error" time=2025-12-03T21:10:10.774-08:00 level=INFO source=runner.go:925 msg="starting ollama engine" time=2025-12-03T21:10:10.775-08:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:56821" time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.alignment default=32 time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.name default="" time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:208 msg="key with type not found" key=general.description default="" time=2025-12-03T21:10:10.804-08:00 level=INFO source=ggml.go:92 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32 time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Fusio\miniforge3\Library\bin time=2025-12-03T21:10:10.830-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ggml.c:1542: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed time=2025-12-03T21:10:11.198-08:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-12-03T21:10:11.342-08:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 0xc0000409" time=2025-12-03T21:10:11.448-08:00 level=ERROR source=sched.go:487 msg="error loading llama server" error="llama runner process has terminated: GGML_ASSERT(type >= 0 && type < GGML_TYPE_COUNT) failed" time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:489 msg="triggering expiration for failed load" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 [GIN] 2025/12/03 - 21:10:11 | 500 | 867.5959ms | 127.0.0.1 | POST "/api/generate" time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:362 msg="runner expired event received" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:377 msg="got lock to unload expired event" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 time=2025-12-03T21:10:11.448-08:00 level=DEBUG source=sched.go:400 msg="starting background wait for VRAM recovery" runner.name=registry.ollama.ai/library/gpt-oss:20b runner.inference=cuda runner.devices=1 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 time=2025-12-03T21:10:11.449-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:11.468-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:11.470-08:00 level=DEBUG source=server.go:1031 msg="stopping llama server" pid=58164 time=2025-12-03T21:10:11.470-08:00 level=DEBUG source=sched.go:405 msg="runner terminated and removed from list, blocking for VRAM recovery" runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2025-12-03T21:10:11.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:11.732-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:11.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:11.997-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:12.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:12.245-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:12.471-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:12.493-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:12.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:12.736-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:12.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:12.985-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:13.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:13.234-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:13.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:13.483-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:13.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:13.746-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:13.971-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:13.992-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:14.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:14.240-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:14.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:14.489-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:14.720-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:14.736-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:14.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:14.982-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:15.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:15.246-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:15.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:15.493-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:15.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:15.742-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:15.970-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:15.992-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:16.220-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:16.239-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:16.470-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.0209205 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=sched.go:408 msg="sending an unloaded event" runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2025-12-03T21:10:16.470-08:00 level=DEBUG source=sched.go:310 msg="ignoring unload event with no pending requests" time=2025-12-03T21:10:16.488-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:16.720-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.271178 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2025-12-03T21:10:16.721-08:00 level=DEBUG source=gpu.go:391 msg="updating system memory data" before.total="31.7 GiB" before.free="15.7 GiB" before.free_swap="28.0 GiB" now.total="31.7 GiB" now.free="15.7 GiB" now.free_swap="28.0 GiB" time=2025-12-03T21:10:16.735-08:00 level=DEBUG source=gpu.go:441 msg="updating cuda memory data" gpu=GPU-f71a72de-823f-4f35-ecec-84e5fc8c07d2 name="NVIDIA GeForce RTX 4090" overhead="0 B" before.total="24.0 GiB" before.free="22.1 GiB" now.total="24.0 GiB" now.free="22.1 GiB" now.used="1.8 GiB" releasing nvml library time=2025-12-03T21:10:16.971-08:00 level=WARN source=sched.go:685 msg="gpu VRAM usage didn't recover within timeout" seconds=5.5215057 runner.size="5.1 GiB" runner.vram="5.1 GiB" runner.parallel=1 runner.pid=58164 runner.model=C:\Users\Fusio\.ollama\models\blobs\sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb [GIN] 2025/12/03 - 21:10:32 | 200 | 4.3786ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/12/03 - 21:11:02 | 200 | 3.7647ms | 127.0.0.1 | GET "/api/tags" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version ollama version is ${PKG_VERSION}
GiteaMirror added the bug label 2026-04-22 18:15:13 -05:00
GiteaMirror commented 2026-04-22 18:15:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 4, 2025):

time=2025-12-03T21:10:01.887-08:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version ${PKG_VERSION})"
time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Fusio\miniforge3\Library\bin

This doesn't look like an ollama release. Try installing the official release.

<!-- gh-comment-id:3611693780 --> @rick-github commented on GitHub (Dec 4, 2025): ``` time=2025-12-03T21:10:01.887-08:00 level=INFO source=routes.go:1357 msg="Listening on 127.0.0.1:11434 (version ${PKG_VERSION})" time=2025-12-03T21:10:10.804-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\Fusio\miniforge3\Library\bin ``` This doesn't look like an ollama release. Try installing the [official release](https://ollama.com/download/windows).
GiteaMirror commented 2026-04-22 18:15:15 -05:00
Author
Owner
Copy Link

@benmishkanian commented on GitHub (Dec 5, 2025):

Thanks for the tip! It seems that Powershell was automatically loading a conda environment that had some other ollama and I guess it conflicts somehow. It looks like it works when I do not initialize the conda environment.

<!-- gh-comment-id:3615119028 --> @benmishkanian commented on GitHub (Dec 5, 2025): Thanks for the tip! It seems that Powershell was automatically loading a conda environment that had some other ollama and I guess it conflicts somehow. It looks like it works when I do not initialize the conda environment.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34561
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?