github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3636] New Gemma:7B crashes ollama server when using open-webui #28001

New Issue
Closed
opened 2026-04-22 05:43:04 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 05:43:04 -05:00
Owner
Copy Link

Originally created by @dewrama on GitHub (Apr 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3636

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Ollama works well with all models. With recent gemma:7b update, running query using open-webui crashes ollama (other models are fine). I have to restart ollama after crash. I verified old version of gemma:7b works (only with recent updated version). If there is an error, system should catch it and throw error code then continue. Crashing the entire server running an inference should not happen.

Ollama log
time=2024-04-12T21:31:40.000-07:00 level=WARN source=server.go:113 msg="server crash 12 - exit code 3221226505 - respawning"

{"function":"initialize","level":"INFO","line":444,"msg":"initializing slots","n_slots":1,"tid":"37388","timestamp":1712982626}
{"function":"initialize","level":"INFO","line":456,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"37388","timestamp":1712982626}
time=2024-04-12T21:30:26.332-07:00 level=INFO source=dyn_ext_server.go:159 msg="Starting llama main loop"
{"function":"update_slots","level":"INFO","line":1574,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"42304","timestamp":1712982626}
{"function":"launch_slot_with_data","level":"INFO","line":829,"msg":"slot is processing task","slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626}
{"function":"update_slots","ga_i":0,"level":"INFO","line":1812,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":44,"slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626}
{"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626}
CUDA error: out of memory
current device: 0, in function alloc at C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:532
cuMemSetAccess(pool_addr + pool_size, reserve_size, &access, 1)
GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:193: !"CUDA error"

What did you expect to see?

No response

Steps to reproduce

No response

Are there any recent changes that introduced the issue?

No response

OS

Windows

Architecture

amd64

Platform

No response

Ollama version

0.1.31

GPU

Nvidia

GPU info

geforce RTX 4060 8gig vram

CPU

No response

Other software

No response

Originally created by @dewrama on GitHub (Apr 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3636 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Ollama works well with all models. With recent gemma:7b update, running query using open-webui crashes ollama (other models are fine). I have to restart ollama after crash. I verified old version of gemma:7b works (only with recent updated version). If there is an error, system should catch it and throw error code then continue. Crashing the entire server running an inference should not happen. Ollama log time=2024-04-12T21:31:40.000-07:00 level=WARN source=server.go:113 msg="server crash 12 - exit code 3221226505 - respawning" {"function":"initialize","level":"INFO","line":444,"msg":"initializing slots","n_slots":1,"tid":"37388","timestamp":1712982626} {"function":"initialize","level":"INFO","line":456,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"37388","timestamp":1712982626} time=2024-04-12T21:30:26.332-07:00 level=INFO source=dyn_ext_server.go:159 msg="Starting llama main loop" {"function":"update_slots","level":"INFO","line":1574,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"42304","timestamp":1712982626} {"function":"launch_slot_with_data","level":"INFO","line":829,"msg":"slot is processing task","slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626} {"function":"update_slots","ga_i":0,"level":"INFO","line":1812,"msg":"slot progression","n_past":0,"n_past_se":0,"n_prompt_tokens_processed":44,"slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626} {"function":"update_slots","level":"INFO","line":1836,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":0,"tid":"42304","timestamp":1712982626} CUDA error: out of memory current device: 0, in function alloc at C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:532 cuMemSetAccess(pool_addr + pool_size, reserve_size, &access, 1) GGML_ASSERT: C:\a\ollama\ollama\llm\llama.cpp\ggml-cuda.cu:193: !"CUDA error" ### What did you expect to see? _No response_ ### Steps to reproduce _No response_ ### Are there any recent changes that introduced the issue? _No response_ ### OS Windows ### Architecture amd64 ### Platform _No response_ ### Ollama version 0.1.31 ### GPU Nvidia ### GPU info geforce RTX 4060 8gig vram ### CPU _No response_ ### Other software _No response_
GiteaMirror added the nvidiabug labels 2026-04-22 05:43:04 -05:00
GiteaMirror commented 2026-04-22 05:43:07 -05:00
Author
Owner
Copy Link

@ycyy commented on GitHub (Apr 18, 2024):

#3232 Update to version 0.1.32 for testing.

<!-- gh-comment-id:2063046246 --> @ycyy commented on GitHub (Apr 18, 2024): #3232 Update to version 0.1.32 for testing.
GiteaMirror commented 2026-04-22 05:43:08 -05:00
Author
Owner
Copy Link

@dewrama commented on GitHub (Apr 18, 2024):

Thanks. I updated yesterday and verified it is version 0.1.32. Still crashing with same issue only for gemma:7b latest.

<!-- gh-comment-id:2063161716 --> @dewrama commented on GitHub (Apr 18, 2024): Thanks. I updated yesterday and verified it is version 0.1.32. Still crashing with same issue only for gemma:7b latest.
GiteaMirror commented 2026-04-22 05:43:08 -05:00
Author
Owner
Copy Link

@ycyy commented on GitHub (Apr 19, 2024):

Thanks. I updated yesterday and verified it is version 0.1.32. Still crashing with same issue only for gemma:7b latest.

Perhaps you could upload the complete logs and have the developers investigate further.

<!-- gh-comment-id:2065604085 --> @ycyy commented on GitHub (Apr 19, 2024): > Thanks. I updated yesterday and verified it is version 0.1.32. Still crashing with same issue only for gemma:7b latest. Perhaps you could upload the complete logs and have the developers investigate further.
GiteaMirror commented 2026-04-22 05:43:10 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 1, 2024):

I believe this should be resolved in the latest release.

If you're still seeing the crash, please share the following and I'll re-open.

Quit the ollama tray application, and then run the following in one powershell terminal

$env:OLLAMA_DEBUG="1"
ollama serve  2>&1 | % ToString | Tee-Object server.log

then in another terminal ollama run gemma:7b and share the server.log so we can see why it's getting the memory prediction wrong.

<!-- gh-comment-id:2143633502 --> @dhiltgen commented on GitHub (Jun 1, 2024): I believe this should be resolved in the latest release. If you're still seeing the crash, please share the following and I'll re-open. Quit the ollama tray application, and then run the following in one powershell terminal ``` $env:OLLAMA_DEBUG="1" ollama serve 2>&1 | % ToString | Tee-Object server.log ``` then in another terminal `ollama run gemma:7b` and share the server.log so we can see why it's getting the memory prediction wrong.
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 nvidia
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#28001
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?