github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6670] expose slots data through API #66234

New Issue
Closed
opened 2026-05-04 01:06:10 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 01:06:10 -05:00
Owner
Copy Link

Originally created by @commit4ever on GitHub (Sep 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6670

hI

Can the information that can be seen in the logs be exposed through /slots api per server/port ? We need this to manage queuing in our load balancer. This has been exposed by llama cpp already. https://github.com/ggerganov/llama.cpp/tree/master/examples/server#get-slots-returns-the-current-slots-processing-state

DEBUG [update_slots] all slots are idle and system prompt is empty, clear the KV cache | tid="140031137009664" timestamp=1725608401
DEBUG [process_single_task] slot data | n_idle_slots=3 n_processing_slots=0 task_id=0 tid="140031137009664" timestamp=1725608401

Many thanks!

Originally created by @commit4ever on GitHub (Sep 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6670 hI Can the information that can be seen in the logs be exposed through /slots api per server/port ? We need this to manage queuing in our load balancer. This has been exposed by llama cpp already. https://github.com/ggerganov/llama.cpp/tree/master/examples/server#get-slots-returns-the-current-slots-processing-state DEBUG [update_slots] all slots are idle and system prompt is empty, clear the KV cache | tid="140031137009664" timestamp=1725608401 DEBUG [process_single_task] slot data | n_idle_slots=3 n_processing_slots=0 task_id=0 tid="140031137009664" timestamp=1725608401 Many thanks!
GiteaMirror added the feature request label 2026-05-04 01:06:11 -05:00
GiteaMirror commented 2026-05-04 01:08:13 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 6, 2024):

We're aiming to switch to a new server implementation written in go, which wont use the same slot construct as server.cpp. That said, this feels like a variation on #2004 which we should be able to start looking at once we've completed the transition.

<!-- gh-comment-id:2334331571 --> @dhiltgen commented on GitHub (Sep 6, 2024): We're aiming to switch to a [new server implementation written in go](https://github.com/ollama/ollama/pull/5034), which wont use the same slot construct as server.cpp. That said, this feels like a variation on #2004 which we should be able to start looking at once we've completed the transition.
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#66234
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?