github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11357] Ollama crashed in Intel shared GPU #69551

New Issue
Closed
opened 2026-05-04 18:26:49 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 18:26:49 -05:00
Owner
Copy Link

Originally created by @mendickmorningstar on GitHub (Jul 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11357

What is the issue?

The ollama crashed in Intel shared GPU.

server.log

Relevant log output

[GIN] 2025/07/10 - 19:24:12 | 200 |    5.1194644s |       127.0.0.1 | POST     "/api/generate"
decode: cannot decode batches with this context (use llama_encode() instead)
Native API failed. Native API returns: 20 (UR_RESULT_ERROR_DEVICE_LOST)
Exception caught at file:D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\ggml-sycl.cpp, line:432, func:operator()
SYCL error: CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, data, size).wait()): Exception caught in this line of code.
  in function ggml_backend_sycl_buffer_set_tensor at D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\ggml-sycl.cpp:432
D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\..\ggml-sycl\common.hpp:115: SYCL error
[GIN] 2025/07/10 - 19:24:24 | 500 |      2.16119s |       127.0.0.1 | POST     "/api/embed"
time=2025-07-10T19:24:24.128+08:00 level=ERROR source=server.go:484 msg="llama runner terminated" error="exit status 0xc0000409"

OS

Windows

GPU

Intel

CPU

Intel

Ollama version

0.9.3

Originally created by @mendickmorningstar on GitHub (Jul 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11357 ### What is the issue? The ollama crashed in Intel shared GPU. [server.log](https://github.com/user-attachments/files/21162153/server.log) ### Relevant log output ```shell [GIN] 2025/07/10 - 19:24:12 | 200 | 5.1194644s | 127.0.0.1 | POST "/api/generate" decode: cannot decode batches with this context (use llama_encode() instead) Native API failed. Native API returns: 20 (UR_RESULT_ERROR_DEVICE_LOST) Exception caught at file:D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\ggml-sycl.cpp, line:432, func:operator() SYCL error: CHECK_TRY_ERROR((*stream).memcpy((char *) tensor->data + offset, data, size).wait()): Exception caught in this line of code. in function ggml_backend_sycl_buffer_set_tensor at D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\ggml-sycl.cpp:432 D:\actions-runner\release-cpp-oneapi_2024_2\_work\llm.cpp\llm.cpp\ollama-llama-cpp\ggml\src\ggml-sycl\..\ggml-sycl\common.hpp:115: SYCL error [GIN] 2025/07/10 - 19:24:24 | 500 | 2.16119s | 127.0.0.1 | POST "/api/embed" time=2025-07-10T19:24:24.128+08:00 level=ERROR source=server.go:484 msg="llama runner terminated" error="exit status 0xc0000409" ``` ### OS Windows ### GPU Intel ### CPU Intel ### Ollama version 0.9.3
GiteaMirror added the bug label 2026-05-04 18:26:49 -05:00
GiteaMirror commented 2026-05-04 18:26:52 -05:00
Author
Owner
Copy Link

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

SYCL is not a supported backend for ollama. I'm guessing that you are using ipex-llm, in which case you can file an issue in their tracker here.

<!-- gh-comment-id:3057191641 --> @rick-github commented on GitHub (Jul 10, 2025): SYCL is not a supported backend for ollama. I'm guessing that you are using ipex-llm, in which case you can file an issue in their tracker [here](https://github.com/intel/ipex-llm/issues).
GiteaMirror commented 2026-05-04 18:26:53 -05:00
Author
Owner
Copy Link

@mendickmorningstar commented on GitHub (Jul 10, 2025):

SYCL is not a supported backend for ollama. I'm guessing that you are using ipex-llm, in which case you can file an issue in their tracker here.

I opened a new ticket for intel-llm.
https://github.com/intel/ipex-llm/issues/13252

<!-- gh-comment-id:3057532965 --> @mendickmorningstar commented on GitHub (Jul 10, 2025): > SYCL is not a supported backend for ollama. I'm guessing that you are using ipex-llm, in which case you can file an issue in their tracker [here](https://github.com/intel/ipex-llm/issues). I opened a new ticket for intel-llm. https://github.com/intel/ipex-llm/issues/13252
GiteaMirror commented 2026-05-04 18:26:54 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 11, 2025):

cc @dhiltgen

<!-- gh-comment-id:3063304736 --> @pdevine commented on GitHub (Jul 11, 2025): cc @dhiltgen
GiteaMirror commented 2026-05-04 18:26:55 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 31, 2025):

Looks like it's fixed in ipex-llm.

<!-- gh-comment-id:3141653085 --> @dhiltgen commented on GitHub (Jul 31, 2025): Looks like it's fixed in ipex-llm.
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#69551
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?