Skip to content

Support GPU pinning for LoRA#8697

Merged
zhyncs merged 6 commits intomainfrom
lifuhuang/lora-pin
Aug 7, 2025
Merged

Support GPU pinning for LoRA#8697
zhyncs merged 6 commits intomainfrom
lifuhuang/lora-pin

Conversation

@lifuhuang
Copy link
Copy Markdown
Collaborator

@lifuhuang lifuhuang commented Aug 2, 2025

Motivation

See #8695

Modifications

Add new boolean parameter pinned to indicate whether adapter should be pinned to memory.

TODO:
- Add UT & docs after #8650 is merged.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

@lifuhuang lifuhuang changed the title Support GPU pinning for LoRA [WIP] Support GPU pinning for LoRA Aug 2, 2025
@lifuhuang lifuhuang changed the title [WIP] Support GPU pinning for LoRA Support GPU pinning for LoRA Aug 2, 2025
@lifuhuang lifuhuang mentioned this pull request Jul 27, 2025
26 tasks
Comment thread docs/backend/lora.ipynb
Copy link
Copy Markdown
Collaborator

@Fridge003 Fridge003 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@zhyncs
Copy link
Copy Markdown
Collaborator

zhyncs commented Aug 4, 2025

@Fridge003 please rebase

@Fridge003 Fridge003 added the ready-to-merge The PR is ready to merge after the CI is green. label Aug 4, 2025
@zhyncs zhyncs merged commit 6210e2c into main Aug 7, 2025
120 of 141 checks passed
@zhyncs zhyncs deleted the lifuhuang/lora-pin branch August 7, 2025 02:39
@lifuhuang lifuhuang mentioned this pull request Aug 10, 2025
1 task
narutolhy pushed a commit to narutolhy/sglang that referenced this pull request Aug 17, 2025
MahmoudAshraf97 pushed a commit to MahmoudAshraf97/sglang that referenced this pull request Sep 8, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ready-to-merge The PR is ready to merge after the CI is green.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants