github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14085] Qwen3-coder-Next:CUDA error:an illegal memory access was encountered on 0.15.5-rc3(Windows) #71256

New Issue
Closed
opened 2026-05-05 00:57:31 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 00:57:31 -05:00
Owner
Copy Link

Originally created by @Attect on GitHub (Feb 5, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14085

What is the issue?

A cuda error while generate.
CPU:AMD 7950X
MEM:128G
GPU:RTX 3090
Windows 11 25H2
OLLAMA:0.15.5-rc3
MODEL:qwen3-coder-next

Relevant log output

[GIN] 2026/02/05 - 11:06:46 | 200 |   30.0556278s |       127.0.0.1 | POST     "/api/generate"
time=2026-02-05T11:06:46.478+08:00 level=DEBUG source=sched.go:557 msg="context for request finished"
time=2026-02-05T11:06:46.478+08:00 level=DEBUG source=sched.go:310 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/qwen3-coder-next:latest runner.inference="[{ID:GPU-9b5c78bb-c978-5e14-c6fa-a71074d1f71a Library:CUDA}]" runner.size="57.9 GiB" runner.vram="20.0 GiB" runner.parallel=1 runner.pid=96688 runner.model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb runner.num_ctx=256000 duration=5m0s
time=2026-02-05T11:06:46.479+08:00 level=DEBUG source=sched.go:328 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3-coder-next:latest runner.inference="[{ID:GPU-9b5c78bb-c978-5e14-c6fa-a71074d1f71a Library:CUDA}]" runner.size="57.9 GiB" runner.vram="20.0 GiB" runner.parallel=1 runner.pid=96688 runner.model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb runner.num_ctx=256000 refCount=0
time=2026-02-05T11:07:01.227+08:00 level=DEBUG source=sched.go:698 msg="evaluating already loaded" model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb
time=2026-02-05T11:07:01.241+08:00 level=DEBUG source=server.go:1535 msg="completion request" images=0 prompt=89 format=""
time=2026-02-05T11:07:01.255+08:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=0 prompt=16 used=0 remaining=16
ggml_cuda_compute_forward: PAD failed
CUDA error: an illegal memory access was encountered
  current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2882
  err
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.15.5-rc3

Originally created by @Attect on GitHub (Feb 5, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14085 ### What is the issue? A cuda error while generate. CPU:AMD 7950X MEM:128G GPU:RTX 3090 Windows 11 25H2 OLLAMA:0.15.5-rc3 MODEL:qwen3-coder-next ### Relevant log output ```shell [GIN] 2026/02/05 - 11:06:46 | 200 | 30.0556278s | 127.0.0.1 | POST "/api/generate" time=2026-02-05T11:06:46.478+08:00 level=DEBUG source=sched.go:557 msg="context for request finished" time=2026-02-05T11:06:46.478+08:00 level=DEBUG source=sched.go:310 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/qwen3-coder-next:latest runner.inference="[{ID:GPU-9b5c78bb-c978-5e14-c6fa-a71074d1f71a Library:CUDA}]" runner.size="57.9 GiB" runner.vram="20.0 GiB" runner.parallel=1 runner.pid=96688 runner.model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb runner.num_ctx=256000 duration=5m0s time=2026-02-05T11:06:46.479+08:00 level=DEBUG source=sched.go:328 msg="after processing request finished event" runner.name=registry.ollama.ai/library/qwen3-coder-next:latest runner.inference="[{ID:GPU-9b5c78bb-c978-5e14-c6fa-a71074d1f71a Library:CUDA}]" runner.size="57.9 GiB" runner.vram="20.0 GiB" runner.parallel=1 runner.pid=96688 runner.model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb runner.num_ctx=256000 refCount=0 time=2026-02-05T11:07:01.227+08:00 level=DEBUG source=sched.go:698 msg="evaluating already loaded" model=C:\ProgramData\ollama\blobs\sha256-30e51a7cb1cf1333b9e298b90b4c7790fe2572d8736b002482a0ac96328a2ffb time=2026-02-05T11:07:01.241+08:00 level=DEBUG source=server.go:1535 msg="completion request" images=0 prompt=89 format="" time=2026-02-05T11:07:01.255+08:00 level=DEBUG source=cache.go:151 msg="loading cache slot" id=0 cache=0 prompt=16 used=0 remaining=16 ggml_cuda_compute_forward: PAD failed CUDA error: an illegal memory access was encountered current device: 0, in function ggml_cuda_compute_forward at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:2882 err C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:94: CUDA error ``` ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.15.5-rc3
GiteaMirror added the bug label 2026-05-05 00:57:31 -05:00
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#71256
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?