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 #9531] cuda driver library failed to get device context 800 #6218

New Issue
Open
opened 2026-04-12 17:37:11 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 17:37:11 -05:00
Owner
Copy Link

Originally created by @sysuls1 on GitHub (Mar 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9531

What is the issue?

{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.187Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.189Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.192Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.194Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.197Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"releasing cuda driver library\n"
{"log":"time=2025-03-06T02:51:22.432Z level=DEBUG source=gpu.go:406 msg="updating system memory data" before.total="503.5 GiB" before.free="439.8 GiB" before.free_swap="2.0 GiB" now.total="503.5 GiB" now.free="439.8 GiB" now.free_swap="2.0 GiB"\n"
{"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n"
{"log":"dlsym: cuInit - 0x7427194c2520\n"
{"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n"
{"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n"
{"log":"dlsym: cuDeviceGet - 0x7427194c2560\n"
{"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n"
{"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n"
{"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n"
{"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n"
{"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n"
{"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n"
{"log":"calling cuInit\n"
{"log":"calling cuDriverGetVersion\n"
{"log":"raw version 0x2ef4\n"
{"log":"CUDA driver version: 12.2\n"
{"log":"calling cuDeviceGetCount\n"
{"log":"device count 5\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.438Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.442Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.445Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.447Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.450Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"releasing cuda driver library\n"
{"log":"time=2025-03-06T02:51:22.681Z level=DEBUG source=gpu.go:406 msg="updating system memory data" before.total="503.5 GiB" before.free="439.8 GiB" before.free_swap="2.0 GiB" now.total="503.5 GiB" now.free="439.8 GiB" now.free_swap="2.0 GiB"\n"
{"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n"
{"log":"dlsym: cuInit - 0x7427194c2520\n"
{"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n"
{"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n"
{"log":"dlsym: cuDeviceGet - 0x7427194c2560\n"
{"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n"
{"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n"
{"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n"
{"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n"
{"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n"
{"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n"
{"log":"calling cuInit\n"
{"log":"calling cuDriverGetVersion\n"
{"log":"raw version 0x2ef4\n"
{"log":"CUDA driver version: 12.2\n"
{"log":"calling cuDeviceGetCount\n"
{"log":"device count 5\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.685Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.688Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.690Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.693Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.695Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"releasing cuda driver library\n"
{"log":"time=2025-03-06T02:51:22.932Z level=DEBUG source=gpu.go:406 msg="updating system memory data" before.total="503.5 GiB" before.free="439.8 GiB" before.free_swap="2.0 GiB" now.total="503.5 GiB" now.free="439.8 GiB" now.free_swap="2.0 GiB"\n"
{"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n"
{"log":"dlsym: cuInit - 0x7427194c2520\n"
{"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n"
{"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n"
{"log":"dlsym: cuDeviceGet - 0x7427194c2560\n"
{"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n"
{"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n"
{"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n"
{"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n"
{"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n"
{"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n"
{"log":"calling cuInit\n"
{"log":"calling cuDriverGetVersion\n"
{"log":"raw version 0x2ef4\n"
{"log":"CUDA driver version: 12.2\n"
{"log":"calling cuDeviceGetCount\n"
{"log":"device count 5\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.938Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.943Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.945Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.948Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.950Z level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"\n"
{"log":"releasing cuda driver library\n"
docker运行一段时间后，强制加载在显存中的模型会自动卸载，并且无法使用GPU。要重启docker，才能正常运行，一段时间后又会出现同样的问题。应该如何解决？

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @sysuls1 on GitHub (Mar 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9531 ### What is the issue? {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.187Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.189Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.192Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.194Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.197Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"releasing cuda driver library\n" {"log":"time=2025-03-06T02:51:22.432Z level=DEBUG source=gpu.go:406 msg=\"updating system memory data\" before.total=\"503.5 GiB\" before.free=\"439.8 GiB\" before.free_swap=\"2.0 GiB\" now.total=\"503.5 GiB\" now.free=\"439.8 GiB\" now.free_swap=\"2.0 GiB\"\n" {"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n" {"log":"dlsym: cuInit - 0x7427194c2520\n" {"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n" {"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n" {"log":"dlsym: cuDeviceGet - 0x7427194c2560\n" {"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n" {"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n" {"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n" {"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n" {"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n" {"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n" {"log":"calling cuInit\n" {"log":"calling cuDriverGetVersion\n" {"log":"raw version 0x2ef4\n" {"log":"CUDA driver version: 12.2\n" {"log":"calling cuDeviceGetCount\n" {"log":"device count 5\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.438Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.442Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.445Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.447Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.450Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"releasing cuda driver library\n" {"log":"time=2025-03-06T02:51:22.681Z level=DEBUG source=gpu.go:406 msg=\"updating system memory data\" before.total=\"503.5 GiB\" before.free=\"439.8 GiB\" before.free_swap=\"2.0 GiB\" now.total=\"503.5 GiB\" now.free=\"439.8 GiB\" now.free_swap=\"2.0 GiB\"\n" {"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n" {"log":"dlsym: cuInit - 0x7427194c2520\n" {"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n" {"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n" {"log":"dlsym: cuDeviceGet - 0x7427194c2560\n" {"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n" {"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n" {"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n" {"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n" {"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n" {"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n" {"log":"calling cuInit\n" {"log":"calling cuDriverGetVersion\n" {"log":"raw version 0x2ef4\n" {"log":"CUDA driver version: 12.2\n" {"log":"calling cuDeviceGetCount\n" {"log":"device count 5\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.685Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.688Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.690Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.693Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.695Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"releasing cuda driver library\n" {"log":"time=2025-03-06T02:51:22.932Z level=DEBUG source=gpu.go:406 msg=\"updating system memory data\" before.total=\"503.5 GiB\" before.free=\"439.8 GiB\" before.free_swap=\"2.0 GiB\" now.total=\"503.5 GiB\" now.free=\"439.8 GiB\" now.free_swap=\"2.0 GiB\"\n" {"log":"initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.183.01\n" {"log":"dlsym: cuInit - 0x7427194c2520\n" {"log":"dlsym: cuDriverGetVersion - 0x7427194c2540\n" {"log":"dlsym: cuDeviceGetCount - 0x7427194c2580\n" {"log":"dlsym: cuDeviceGet - 0x7427194c2560\n" {"log":"dlsym: cuDeviceGetAttribute - 0x7427194c2660\n" {"log":"dlsym: cuDeviceGetUuid - 0x7427194c25c0\n" {"log":"dlsym: cuDeviceGetName - 0x7427194c25a0\n" {"log":"dlsym: cuCtxCreate_v3 - 0x7427194ca220\n" {"log":"dlsym: cuMemGetInfo_v2 - 0x7427194d56f0\n" {"log":"dlsym: cuCtxDestroy - 0x7427195246f0\n" {"log":"calling cuInit\n" {"log":"calling cuDriverGetVersion\n" {"log":"raw version 0x2ef4\n" {"log":"CUDA driver version: 12.2\n" {"log":"calling cuDeviceGetCount\n" {"log":"device count 5\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.938Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.943Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.945Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.948Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"cuda driver library failed to get device context 800time=2025-03-06T02:51:22.950Z level=WARN source=gpu.go:449 msg=\"error looking up nvidia GPU memory\"\n" {"log":"releasing cuda driver library\n" docker运行一段时间后，强制加载在显存中的模型会自动卸载，并且无法使用GPU。要重启docker，才能正常运行，一段时间后又会出现同样的问题。应该如何解决？ ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-12 17:37:11 -05:00
GiteaMirror commented 2026-04-12 17:37:16 -05:00
Author
Owner
Copy Link

@yyalon commented on GitHub (Apr 16, 2025):

I've encountered the same issue. I'm using Docker to run Ollama and loading the qwq model on Ubuntu 22.04 with an A6000 GPU.

<!-- gh-comment-id:2808117040 --> @yyalon commented on GitHub (Apr 16, 2025): I've encountered the same issue. I'm using Docker to run Ollama and loading the qwq model on Ubuntu 22.04 with an A6000 GPU.
GiteaMirror commented 2026-04-12 17:37:18 -05:00
Author
Owner
Copy Link

@ER-EPR commented on GitHub (May 8, 2025):

can be solved by same here

<!-- gh-comment-id:2861661442 --> @ER-EPR commented on GitHub (May 8, 2025): can be solved by [same here](https://github.com/ollama/ollama/issues/6928#issuecomment-2586208913)
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#6218
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?