Repository navigation
Conversation
Signed-off-by: Yuki Huang <yukih@nvidia.com>
yuki-97
added
the
CI:Lfast
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
Signed-off-by: Yuki Huang <yukih@nvidia.com>
yuki-97
force-pushed
the
yukih/vllm-multiple-frontends
branch
from
November 4, 2026 17:02
a244a4b to
cf2b716
Compare
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do ?
Scale HTTP request handling and tokenization with multiple frontend processes sharing one vLLM engine. Single-frontend behavior remains the default.
What changed
1. Add shared-engine HTTP serving. Set
vllm_cfg.http_api_server_countabove one with async HTTP serving enabled. All frontends share one listening socket.2. Synchronize frontend state. Broadcast token-capture setup and rollout weight versions to every frontend, and aggregate multiprocess Prometheus metrics.
Validation: Ruff checks and formatting pass. GPU validation is pending.