github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-11 18:55:36 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2876] REST APIs Request Cancellation #1757

New Issue
Closed
opened 2026-04-12 11:46:02 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 11:46:02 -05:00
Owner
Copy Link

Originally created by @mAlaliSy on GitHub (Mar 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2876

Hi there,
I am using Ollama and I found it awesome.

One question, when calling Ollama using REST APIs (i.e. generate API), if the client cancels the HTTP request, will Ollama stop processing the request?

I found this issue here for JS client library https://github.com/ollama/ollama-js/issues/39 but it doesn't mention what happens on the server when the client abort the request.

Originally created by @mAlaliSy on GitHub (Mar 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2876 Hi there, I am using Ollama and I found it awesome. One question, when calling Ollama using REST APIs (i.e. generate API), if the client cancels the HTTP request, will Ollama stop processing the request? I found this issue here for JS client library https://github.com/ollama/ollama-js/issues/39 but it doesn't mention what happens on the server when the client abort the request.
GiteaMirror commented 2026-04-12 11:46:05 -05:00
Author
Owner
Copy Link

@mmo80 commented on GitHub (Mar 2, 2024):

In my experience, yes, the server stops responding (not crashing) to the request if it is cancelled. That's what I see in the Ollama server logs when, for example, a stream fetch is cancelled (using AbortController); the server immediately stops responding.

<!-- gh-comment-id:1974835142 --> @mmo80 commented on GitHub (Mar 2, 2024): In my experience, yes, the server stops responding (not crashing) to the request if it is cancelled. That's what I see in the Ollama server logs when, for example, a stream fetch is cancelled (using [AbortController](https://developer.mozilla.org/en-US/docs/Web/API/AbortController)); the server immediately stops responding.
GiteaMirror commented 2026-04-12 11:46:06 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Mar 12, 2024):

Yes! If you abort the request Ollama will stop generation. Hope this helps!

<!-- gh-comment-id:1989771389 --> @jmorganca commented on GitHub (Mar 12, 2024): Yes! If you abort the request Ollama will stop generation. Hope this helps!
GiteaMirror commented 2026-04-12 11:46:07 -05:00
Author
Owner
Copy Link

@nkeilar commented on GitHub (Mar 25, 2024):

@jmorganca I've found that it doesn't stop in all cases. If some of the work is offloaded to the CPU, it seems to continue executing. This may have fried my CPU as it kept running without my knowledge while I was away, and probably didn't have adequate cooling in the room (13900k). Just replaced cpu and mobo. And am anxious that its its just going to run endlessly doing long generations on CPU. Need confidence that it stops when stream is closed, or stop button pressed.

This was verified below my comment here: https://github.com/open-webui/open-webui/issues/1166#issuecomment-2016954654 - actually reporting, as had significant financial cost to me.

Specifically I was using the professor model, quantised to 2 bits to fit on dual GPU, but it doesn't quite fit so I am offloading a bunch of layers to the CPU. I tested after replacing my CPU and Mobo, and its still occurring.

<!-- gh-comment-id:2017043630 --> @nkeilar commented on GitHub (Mar 25, 2024): @jmorganca I've found that it doesn't stop in all cases. If some of the work is offloaded to the CPU, it seems to continue executing. This may have fried my CPU as it kept running without my knowledge while I was away, and probably didn't have adequate cooling in the room (13900k). Just replaced cpu and mobo. And am anxious that its its just going to run endlessly doing long generations on CPU. Need confidence that it stops when stream is closed, or stop button pressed. This was verified below my comment here: https://github.com/open-webui/open-webui/issues/1166#issuecomment-2016954654 - actually reporting, as had significant financial cost to me. Specifically I was using the professor model, quantised to 2 bits to fit on dual GPU, but it doesn't quite fit so I am offloading a bunch of layers to the CPU. I tested after replacing my CPU and Mobo, and its still occurring.
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
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#1757
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?