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 #7329] Terminate the current task after the REST request is actively ended #4656

New Issue
Closed
opened 2026-04-12 15:34:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 15:34:31 -05:00
Owner
Copy Link

Originally created by @viosay on GitHub (Oct 23, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7329

Can the current executing task be terminated after a REST request is actively interrupted?

Originally created by @viosay on GitHub (Oct 23, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7329 Can the current executing task be terminated after a REST request is actively interrupted?
GiteaMirror added the question label 2026-04-12 15:34:31 -05:00
GiteaMirror commented 2026-04-12 15:34:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 23, 2024):

Seems to do that now. If I start nvtop and then run

curl -s localhost:11434/api/generate -d '{"model":"llama3.1","prompt":"write a long story about a unicorn lost in a rainforest"}'

I see GPU usage go to 90%, and drop back to 0 immediately after I ^C the curl command. When have you observed that it doesn't do this?

<!-- gh-comment-id:2431718566 --> @rick-github commented on GitHub (Oct 23, 2024): Seems to do that now. If I start `nvtop` and then run ``` curl -s localhost:11434/api/generate -d '{"model":"llama3.1","prompt":"write a long story about a unicorn lost in a rainforest"}' ``` I see GPU usage go to 90%, and drop back to 0 immediately after I ^C the curl command. When have you observed that it doesn't do this?
GiteaMirror commented 2026-04-12 15:34:34 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 23, 2024):

In addition to what Rick mentioned, the default timeout for models is 5 minutes, so we will stay loaded on the GPU until that timer expires so we're ready to handle additional requests. You can unload the model immediately with the stop command

<!-- gh-comment-id:2432796271 --> @dhiltgen commented on GitHub (Oct 23, 2024): In addition to what Rick mentioned, the default timeout for models is 5 minutes, so we will stay loaded on the GPU until that timer expires so we're ready to handle additional requests. You can unload the model immediately with the [stop command](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately)
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 question
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#4656
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?