github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[PR #8049] Implement OLLAMA_MAX_KEEP_ALIVE environment variable #43850

New Issue
Open
opened 2026-04-24 23:25:31 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-24 23:25:31 -05:00
Owner
Copy Link

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/8049
Author: @jhbruhn
Created: 12/11/2024
Status: 🔄 Open

Base: main ← Head: maxkeepalive

📝 Commits (1)

  • 09e2a95 feat: Implement OLLAMA_MAX_KEEP_ALIVE environment variable to cap the keep_alive of models to a maximum value

📊 Changes

5 files changed (+72 additions, -1 deletions)

View changed files

📝 cmd/cmd.go (+1 -0)
📝 docs/faq.md (+3 -0)
📝 envconfig/config.go (+23 -0)
📝 envconfig/config_test.go (+33 -0)
📝 server/sched.go (+12 -1)

📄 Description

In cooperative server environments, it is desirable to cap the keep_alive value of models to a maximum duration. This enables server administrators to guarantee that models are unloaded at some point if they are not needed anymore.

For this, I propose to introduce the OLLAMA_MAX_KEEP_ALIVE environment variable, which allows the administrator to specify a maximum keep alive value at which all other requests will be capped. This additionally disallows indefinite loading of models.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/8049 **Author:** [@jhbruhn](https://github.com/jhbruhn) **Created:** 12/11/2024 **Status:** 🔄 Open **Base:** `main` ← **Head:** `maxkeepalive` --- ### 📝 Commits (1) - [`09e2a95`](https://github.com/ollama/ollama/commit/09e2a9526cbb5fd70bed8c331d0028f44b691c82) feat: Implement OLLAMA_MAX_KEEP_ALIVE environment variable to cap the keep_alive of models to a maximum value ### 📊 Changes **5 files changed** (+72 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `cmd/cmd.go` (+1 -0) 📝 `docs/faq.md` (+3 -0) 📝 `envconfig/config.go` (+23 -0) 📝 `envconfig/config_test.go` (+33 -0) 📝 `server/sched.go` (+12 -1) </details> ### 📄 Description In cooperative server environments, it is desirable to cap the keep_alive value of models to a maximum duration. This enables server administrators to guarantee that models are unloaded at _some_ point if they are not needed anymore. For this, I propose to introduce the `OLLAMA_MAX_KEEP_ALIVE` environment variable, which allows the administrator to specify a maximum keep alive value at which all other requests will be capped. This additionally disallows indefinite loading of models. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-24 23:25:31 -05:00
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 pull-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#43850
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?