[Docs] Add multi-thread weight loading documentation#2445
Merged
SamitHuang merged 1 commit intoApr 9, 2026
Conversation
Document the multi-thread weight loading startup optimization introduced in PR vllm-project#1504, including configuration, CLI flags, usage examples, and benchmark results. Made-with: Cursor Signed-off-by: samithuang <285365963@qq.com>
vraiti
pushed a commit
to vraiti/vllm-omni
that referenced
this pull request
Apr 9, 2026
Signed-off-by: samithuang <285365963@qq.com>
Sy0307
pushed a commit
to Sy0307/vllm-omni
that referenced
this pull request
Apr 10, 2026
Signed-off-by: samithuang <285365963@qq.com>
daixinning
pushed a commit
to daixinning/vllm-omni
that referenced
this pull request
Apr 13, 2026
Signed-off-by: samithuang <285365963@qq.com>
lengrongfu
pushed a commit
to lengrongfu/vllm-omni
that referenced
this pull request
May 1, 2026
Signed-off-by: samithuang <285365963@qq.com>
clodaghwalsh17
pushed a commit
to clodaghwalsh17/nm-vllm-omni-ent
that referenced
this pull request
May 12, 2026
Signed-off-by: samithuang <285365963@qq.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
Add documentation for the multi-thread weight loading startup optimization introduced in PR #1504. This feature loads safetensors shards in parallel using a thread pool, reducing model startup time by 5-6x for large diffusion models.
Updates
docs/user_guide/diffusion_features.mdto include:--disable-multithread-weight-load,--num-weight-load-threads) and Python parametersTest Plan
Documentation-only change. Verified markdown rendering and internal anchor links are correct.
Test Result
N/A (docs only).
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model. Please runmkdocs serveto sync the documentation editions to./docs.