fix(docker): patch vLLM v0.23.0 to preserve non-persistent buffers on layerwise reload#326
Open
Josephasafg wants to merge 1 commit into
Open
Conversation
Signed-off-by: Josephasafg <ajgard7@gmail.com>
Josephasafg
force-pushed
the
patch/vllm-reload-nonpersistent-buffers
branch
from
d5873fb to
1be8f6a
Compare
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Backports vllm-project/vllm#44371 into
docker/patch/latest/vllm.patch. Layerwise reload was corrupting unloaded non-persistent buffers during warm weight-sync (surfaced on Gemma, where aroot_sizebuffer drifted 0.0188 → 1.0,spiking trainer↔vLLM KL from 1.52 to 0.008 once fixed).
Patched against vLLM v0.23.0.