github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7758] OLLAMA_MAX_QUEUE does not limit requests to the same model #4954

New Issue
Open
opened 2026-04-12 16:00:49 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:00:49 -05:00
Owner
Copy Link

Originally created by @yyx1111 on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7758

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

It seems that OLLAMA_MAX_QUEUE is not taking effect. My environment is Windows 11, and I have set OLLAMA_NUM_PARALLEL=1,
set OLLAMA_MAX_QUEUE=1, but excessive requests are still queuing up instead of returning an error.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.3.14

Originally created by @yyx1111 on GitHub (Nov 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7758 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? It seems that OLLAMA_MAX_QUEUE is not taking effect. My environment is Windows 11, and I have set OLLAMA_NUM_PARALLEL=1, set OLLAMA_MAX_QUEUE=1, but excessive requests are still queuing up instead of returning an error. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.14
GiteaMirror added the feature request label 2026-04-12 16:00:49 -05:00
GiteaMirror commented 2026-04-12 16:00:51 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 21, 2024):

This is a side effect of the way the scheduler is implemented. The queue depth relates to processing incoming requests that need to be scheduled. If you make requests for different models, then it would have the behavior you're looking for. Multiple requests to the same model pass through the scheduler quickly since the model is already loaded, and get to the underlying runner and queue up on the parallelism semaphore. Currently this layer of the system does not use a fixed depth queue. Adjusting that implementation to use a queue and respect the max queue depth does seem like a good enhancement to make.

<!-- gh-comment-id:2491828367 --> @dhiltgen commented on GitHub (Nov 21, 2024): This is a side effect of the way the scheduler is implemented. The queue depth relates to processing incoming requests that need to be scheduled. If you make requests for different models, then it would have the behavior you're looking for. Multiple requests to the same model pass through the scheduler quickly since the model is already loaded, and get to the underlying runner and queue up on the parallelism semaphore. Currently this layer of the system does not use a fixed depth queue. Adjusting that implementation to use a queue and respect the max queue depth does seem like a good enhancement to make.
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 feature request
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#4954
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?