github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9548] Support hot-swapping for LoRA adapters #52739

New Issue
Open
opened 2026-04-29 00:43:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 00:43:32 -05:00
Owner
Copy Link

Originally created by @anzhexe on GitHub (Mar 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9548

  • I have searched documentation
  • I have checked issues.

Hi,
Regarding Ollama's recent implementation of multiple LoRA adapters support (PR #7667), I'm curious about the possibility of hot-swapping capabilities for these adapters.

For reference, llama.cpp has already implemented this functionality as demonstrated in the following pull requests:

Are there any plans to implement a similar hot-swapping functionality within Ollama?

Originally created by @anzhexe on GitHub (Mar 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9548 - [x] I have searched documentation - [x] I have checked issues. Hi, Regarding Ollama's recent implementation of multiple LoRA adapters support (PR #7667), I'm curious about the possibility of hot-swapping capabilities for these adapters. For reference, llama.cpp has already implemented this functionality as demonstrated in the following pull requests: - https://github.com/ggml-org/llama.cpp/pull/8857 - https://github.com/ggml-org/llama.cpp/pull/10994 Are there any plans to implement a similar hot-swapping functionality within Ollama?
GiteaMirror added the feature request label 2026-04-29 00:43:32 -05:00
GiteaMirror commented 2026-04-29 00:43:36 -05:00
Author
Owner
Copy Link

@mixxxxus commented on GitHub (Dec 20, 2025):

Bumping this.

Please consider runtime LoRA swapping. Being able to change adapters without merging them into the base model would make agent systems much easier to manage.

Even something simple like selecting adapters per request in '/api/chat' would already be great.

<!-- gh-comment-id:3678082597 --> @mixxxxus commented on GitHub (Dec 20, 2025): Bumping this. Please consider runtime LoRA swapping. Being able to **change adapters without merging them into the base model** would make agent systems much easier to manage. Even something simple like selecting adapters per request in '/api/chat' would already be great.
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#52739
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?