github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 06:31:50 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8980] Ollama can't find compatible GPUs on windows 2022 #31588

New Issue
Closed
opened 2026-04-22 12:11:27 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 12:11:27 -05:00
Owner
Copy Link

Originally created by @eren186 on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8980

What is the issue?

Ollama alway uses cpu on windows 2022 / vsphere 7/vgpu/nvidia rtx a6000
have try to reinstall driver and cuda many times.nv

Mon Feb 10 11:54:43 2025
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 538.33 Driver Version: 538.33 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA RTXA6000-48A WDDM | 00000000:02:01.0 On | N/A |
| N/A 0C P8 N/A / N/A | 483MiB / 49152MiB | 1% Prohibited |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 560 C+G ...CBS_cw5n1h2txyewy\TextInputHost.exe N/A |
| 0 N/A N/A 1700 C+G ....Search_cw5n1h2txyewy\SearchApp.exe N/A |
| 0 N/A N/A 3216 C+G C:\Windows\System32\ServerManager.exe N/A |
| 0 N/A N/A 5052 C+G C:\Windows\explorer.exe N/A |
| 0 N/A N/A 6868 C+G ...on\133.0.3065.51\msedgewebview2.exe N/A |
| 0 N/A N/A 7088 C+G ...crosoft\Edge\Application\msedge.exe N/A |
| 0 N/A N/A 8120 C+G ...rcSetup\Systray\AzureArcSysTray.exe N/A |
| 0 N/A N/A 8220 C+G ...siveControlPanel\SystemSettings.exe N/A |
| 0 N/A N/A 8916 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A |
+---------------------------------------------------------------------------------------+

Relevant log output

-------------------------------------log------------------------------------
2025/02/10 11:28:30 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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\\Administrator\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-10T11:28:30.930+08:00 level=INFO source=images.go:432 msg="total blobs: 9"
time=2025-02-10T11:28:30.932+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-10T11:28:30.932+08:00 level=INFO source=routes.go:1238 msg="Listening on 127.0.0.1:11434 (version 0.5.7)"
time=2025-02-10T11:28:30.933+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]"
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=4
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=2 efficiency=0 threads=2
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=2 efficiency=0 threads=2
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=2 cores=2 efficiency=0 threads=2
time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=3 cores=2 efficiency=0 threads=2
time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:283 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801"
time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered"
time=2025-02-10T11:28:30.992+08:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="32.0 GiB" available="29.2 GiB"

------------------------DeviceQuery---------------------------------------
Device 0: "NVIDIA RTXA6000-48A"
  CUDA Driver Version / Runtime Version          12.2 / 12.8
  CUDA Capability Major/Minor version number:    8.6
  Total amount of global memory:                 49152 MBytes (51539148800 bytes)
  (84) Multiprocessors, (128) CUDA Cores/MP:     10752 CUDA Cores
  GPU Max Clock rate:                            1800 MHz (1.80 GHz)
  Memory Clock rate:                             8001 Mhz
  Memory Bus Width:                              384-bit
  L2 Cache Size:                                 6291456 bytes
  Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
  Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
  Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
  Total amount of constant memory:               zu bytes
  Total amount of shared memory per block:       zu bytes
  Total number of registers available per block: 65536
  Warp size:                                     32
  Maximum number of threads per multiprocessor:  1536
  Maximum number of threads per block:           1024
  Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
  Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
  Maximum memory pitch:                          zu bytes
  Texture alignment:                             zu bytes
  Concurrent copy and kernel execution:          Yes with 5 copy engine(s)
  Run time limit on kernels:                     Yes
  Integrated GPU sharing Host Memory:            No
  Support host page-locked memory mapping:       Yes
  Alignment requirement for Surfaces:            Yes
  Device has ECC support:                        Disabled
  CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
  Device supports Unified Addressing (UVA):      Yes
  Device supports Compute Preemption:            No
  Supports Cooperative Kernel Launch:            No
  Supports MultiDevice Co-op Kernel Launch:      No
  Device PCI Domain ID / Bus ID / location ID:   0 / 2 / 1
  Compute Mode:
     < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 12.2, CUDA Runtime Version = 12.8, NumDevs = 1, Device0 = NVIDIA RTXA6000-48A
Result = PASS

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @eren186 on GitHub (Feb 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8980 ### What is the issue? Ollama alway uses cpu on windows 2022 / vsphere 7/vgpu/nvidia rtx a6000 have try to reinstall driver and cuda many times.nv Mon Feb 10 11:54:43 2025 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 538.33 Driver Version: 538.33 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA RTXA6000-48A WDDM | 00000000:02:01.0 On | N/A | | N/A 0C P8 N/A / N/A | 483MiB / 49152MiB | 1% Prohibited | | | | N/A | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 560 C+G ...CBS_cw5n1h2txyewy\TextInputHost.exe N/A | | 0 N/A N/A 1700 C+G ....Search_cw5n1h2txyewy\SearchApp.exe N/A | | 0 N/A N/A 3216 C+G C:\Windows\System32\ServerManager.exe N/A | | 0 N/A N/A 5052 C+G C:\Windows\explorer.exe N/A | | 0 N/A N/A 6868 C+G ...on\133.0.3065.51\msedgewebview2.exe N/A | | 0 N/A N/A 7088 C+G ...crosoft\Edge\Application\msedge.exe N/A | | 0 N/A N/A 8120 C+G ...rcSetup\Systray\AzureArcSysTray.exe N/A | | 0 N/A N/A 8220 C+G ...siveControlPanel\SystemSettings.exe N/A | | 0 N/A N/A 8916 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A | +---------------------------------------------------------------------------------------+ ### Relevant log output ```shell -------------------------------------log------------------------------------ 2025/02/10 11:28:30 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false 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\\Administrator\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-10T11:28:30.930+08:00 level=INFO source=images.go:432 msg="total blobs: 9" time=2025-02-10T11:28:30.932+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-10T11:28:30.932+08:00 level=INFO source=routes.go:1238 msg="Listening on 127.0.0.1:11434 (version 0.5.7)" time=2025-02-10T11:28:30.933+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]" time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=4 time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=2 efficiency=0 threads=2 time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=2 efficiency=0 threads=2 time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=2 cores=2 efficiency=0 threads=2 time=2025-02-10T11:28:30.933+08:00 level=INFO source=gpu_windows.go:214 msg="" package=3 cores=2 efficiency=0 threads=2 time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:283 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801" time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:392 msg="no compatible GPUs were discovered" time=2025-02-10T11:28:30.992+08:00 level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="32.0 GiB" available="29.2 GiB" ------------------------DeviceQuery--------------------------------------- Device 0: "NVIDIA RTXA6000-48A" CUDA Driver Version / Runtime Version 12.2 / 12.8 CUDA Capability Major/Minor version number: 8.6 Total amount of global memory: 49152 MBytes (51539148800 bytes) (84) Multiprocessors, (128) CUDA Cores/MP: 10752 CUDA Cores GPU Max Clock rate: 1800 MHz (1.80 GHz) Memory Clock rate: 8001 Mhz Memory Bus Width: 384-bit L2 Cache Size: 6291456 bytes Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384) Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers Total amount of constant memory: zu bytes Total amount of shared memory per block: zu bytes Total number of registers available per block: 65536 Warp size: 32 Maximum number of threads per multiprocessor: 1536 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535) Maximum memory pitch: zu bytes Texture alignment: zu bytes Concurrent copy and kernel execution: Yes with 5 copy engine(s) Run time limit on kernels: Yes Integrated GPU sharing Host Memory: No Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Disabled CUDA Device Driver Mode (TCC or WDDM): WDDM (Windows Display Driver Model) Device supports Unified Addressing (UVA): Yes Device supports Compute Preemption: No Supports Cooperative Kernel Launch: No Supports MultiDevice Co-op Kernel Launch: No Device PCI Domain ID / Bus ID / location ID: 0 / 2 / 1 Compute Mode: < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) > deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 12.2, CUDA Runtime Version = 12.8, NumDevs = 1, Device0 = NVIDIA RTXA6000-48A Result = PASS ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 12:11:27 -05:00
GiteaMirror commented 2026-04-22 12:11:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 10, 2025):

time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:283 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801"

cudaErrorNotSupported = 801

  • This error indicates the attempted operation is not supported on the current system or device.

Try enabling unified memory: https://docs.nvidia.com/vgpu/13.0/grid-vgpu-user-guide/index.html#enabling-unified-memory-vgpu

<!-- gh-comment-id:2647489342 --> @rick-github commented on GitHub (Feb 10, 2025): ``` time=2025-02-10T11:28:30.991+08:00 level=INFO source=gpu.go:283 msg="error looking up nvidia GPU memory" error="cuda driver library failed to get device context 801" ``` [cudaErrorNotSupported](https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html#group__CUDART__TYPES_1g3f51e3575c2178246db0a94a430e0038:~:text=cudaErrorNotSupported) = 801 - This error indicates the attempted operation is not supported on the current system or device. Try enabling unified memory: https://docs.nvidia.com/vgpu/13.0/grid-vgpu-user-guide/index.html#enabling-unified-memory-vgpu
GiteaMirror commented 2026-04-22 12:11:31 -05:00
Author
Owner
Copy Link

@eren186 commented on GitHub (Feb 10, 2025):

hi @rick-github thanks for reply
after add those settings below
pciPassthru0.cfg.enable_uvm
1
pciPassthru1.cfg.enable_uvm
1
pciPassthru0.cfg.enable_debugging
1
pciPassthru0.cfg.enable_profiling
1
ollama now is working on Gpu.

<!-- gh-comment-id:2648311448 --> @eren186 commented on GitHub (Feb 10, 2025): hi @rick-github thanks for reply after add those settings below pciPassthru0.cfg.enable_uvm 1 pciPassthru1.cfg.enable_uvm 1 pciPassthru0.cfg.enable_debugging 1 pciPassthru0.cfg.enable_profiling 1 ollama now is working on Gpu.
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#31588
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?