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 #1901] "api/generate" stalls after some queries #63130

New Issue
Closed
opened 2026-05-03 12:15:42 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-05-03 12:15:42 -05:00
Owner
Copy Link

Originally created by @oderwat on GitHub (Jan 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1901

I have a strange phenomenon and can't get rid of it without a workaround:

When I call "api/generate" with the same model regularly every some seconds (5s-15s) the API suddenly stops responding after 15-20 calls (which seems to depend on the model size?).

This is reproducible with different models and with both: A WSL2 based server and my iMac based server (I could try it with an M1 Air too but didn't so far). When I run it on the iMac I have high CPU consumption while the API does not return the call. See this CPU display (it shows some of the last working queries until it freezes and does not reply):

Snipaste_2024-01-10_13-51-59

When switching models for the generation or just create an embedding (using the endpoint) with a tiny model and an empty prompt in between, it does work endlessly with the same prompts and code.

I am using current main and also tried to go back some commits, but it seems that this also happens with older commits.

Is there anything I can do to get more information to find out what the problem may be?

Specialities: I use OLLAMA_HOST=0.0.0.0:11434 OLLAMA_ORIGINS="*" on the server and call the API from JavaScript (actually WASM) using the fetch API. I did not try it with another type of HTTP client yet (and can't for this special applications use case).

Originally created by @oderwat on GitHub (Jan 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1901 I have a strange phenomenon and can't get rid of it without a workaround: When I call "api/generate" with the same model regularly every some seconds (5s-15s) the API suddenly stops responding after 15-20 calls (which seems to depend on the model size?). This is reproducible with different models and with both: A WSL2 based server and my iMac based server (I could try it with an M1 Air too but didn't so far). When I run it on the iMac I have high CPU consumption while the API does not return the call. See this CPU display (it shows some of the last working queries until it freezes and does not reply): ![Snipaste_2024-01-10_13-51-59](https://github.com/jmorganca/ollama/assets/719156/f43bdac7-b162-446b-bbb1-77a757c2ec5a) When switching models for the generation or just create an embedding (using the endpoint) with a tiny model and an empty prompt in between, it does work endlessly with the same prompts and code. I am using current main and also tried to go back some commits, but it seems that this also happens with older commits. Is there anything I can do to get more information to find out what the problem may be? Specialities: I use `OLLAMA_HOST=0.0.0.0:11434 OLLAMA_ORIGINS="*"` on the server and call the API from JavaScript (actually WASM) using the fetch API. I did not try it with another type of HTTP client yet (and can't for this special applications use case).
GiteaMirror added the performancebug labels 2026-05-03 12:15:42 -05:00
GiteaMirror commented 2026-05-03 12:15:44 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Jan 10, 2024):

Hi @oderwat Could you tell if you are using 0.1.19?
Thanks

<!-- gh-comment-id:1885178871 --> @igorschlum commented on GitHub (Jan 10, 2024): Hi @oderwat Could you tell if you are using 0.1.19? Thanks
GiteaMirror commented 2026-05-03 12:15:45 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Jan 10, 2024):

@igorschlum I am a Go developer and use the current main branch (34344d801c). I am out of the office soon, but I can verify the behavior with a release version later tonight.

Edit: This is the v0.1.19 release commit. But I will check with a binary later to make sure it is the same with that too.

<!-- gh-comment-id:1885191642 --> @oderwat commented on GitHub (Jan 10, 2024): @igorschlum I am a Go developer and use the current main branch (34344d801ccb2ea1a9a25bbc69576fc9f82211ae). I am out of the office soon, but I can verify the behavior with a release version later tonight. Edit: This is the v0.1.19 release commit. But I will check with a binary later to make sure it is the same with that too.
GiteaMirror commented 2026-05-03 12:15:45 -05:00
Author
Owner
Copy Link

@IAMBUDE commented on GitHub (Jan 10, 2024):

Might be related to #1863

<!-- gh-comment-id:1885301989 --> @IAMBUDE commented on GitHub (Jan 10, 2024): Might be related to #1863
GiteaMirror commented 2026-05-03 12:15:48 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Jan 10, 2024):

@IAMBUDE Yes

I can confirm that installing v0.1.17 gets rid of my problem with hanging queries. It also seems like the generations are faster on my WSL2 machine with RTX 3090 (0.8s-1.5s vs 1.5s-3.5s). I need to double-check that though.

<!-- gh-comment-id:1885574677 --> @oderwat commented on GitHub (Jan 10, 2024): @IAMBUDE Yes I can confirm that installing v0.1.17 gets rid of my problem with hanging queries. It also seems like the generations are faster on my WSL2 machine with RTX 3090 (0.8s-1.5s vs 1.5s-3.5s). I need to double-check that though.
GiteaMirror commented 2026-05-03 12:15:49 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 13, 2024):

Going to go ahead and close the issue.

<!-- gh-comment-id:1996108705 --> @pdevine commented on GitHub (Mar 13, 2024): Going to go ahead and close the issue.
GiteaMirror commented 2026-05-03 12:15:50 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Mar 14, 2024):

@oderwat it would be appreciated if you could confirm whether the issue as been resolved with the current build. If not, please reopen the issue and provide more details to facilitate replication of the issue.
Best,
Igor

<!-- gh-comment-id:1996585934 --> @igorschlum commented on GitHub (Mar 14, 2024): @oderwat it would be appreciated if you could confirm whether the issue as been resolved with the current build. If not, please reopen the issue and provide more details to facilitate replication of the issue. Best, Igor
GiteaMirror commented 2026-05-03 12:15:51 -05:00
Author
Owner
Copy Link

@oderwat commented on GitHub (Mar 14, 2024):

@igorschlum I did not run into this with current versions anymore.

<!-- gh-comment-id:1997296275 --> @oderwat commented on GitHub (Mar 14, 2024): @igorschlum I did not run into this with current versions anymore.
GiteaMirror commented 2026-05-03 12:15:52 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Mar 14, 2024):

OK, thanks.

<!-- gh-comment-id:1997402571 --> @igorschlum commented on GitHub (Mar 14, 2024): OK, thanks.
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 performance
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#63130
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?