fix(pd_vllm): drop stream_options / max_completion_tokens from the prefill request - #54
Closed
WSEmma wants to merge 1 commit into
Closed
fix(pd_vllm): drop stream_options / max_completion_tokens from the prefill request#54WSEmma wants to merge 1 commit into
WSEmma wants to merge 1 commit into
Conversation
WSEmma
force-pushed
the
fix/pd-prefill-drop-contradicting-fields
branch
from
August 5, 2026 07:25
03c9b0f to
35c8782
Compare
WSEmma
changed the title
WSEmma
force-pushed
the
fix/pd-prefill-drop-contradicting-fields
branch
from
August 5, 2026 07:28
35c8782 to
604badd
Compare
mzmssg
approved these changes
Aug 5, 2026
…efill request Supports streaming clients against a PD deployment: the prefill request now drops stream_options and max_completion_tokens from the client body, since the first contradicts the stream=False we force (vLLM rejects the pair with a 400 during body parsing) and the second overrides our max_tokens=1. Verified with `vllm bench serve --backend openai-chat`, which sends both unconditionally and previously failed every request.
WSEmma
force-pushed
the
fix/pd-prefill-drop-contradicting-fields
branch
from
August 5, 2026 07:34
604badd to
9a96655
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Supports streaming clients against a PD deployment: the prefill request now drops
stream_optionsandmax_completion_tokensfrom the client body, since the first contradicts thestream=Falsewe force (vLLM rejects the pair with a 400 during body parsing) and the second overrides ourmax_tokens=1.Verified with
vllm bench serve --backend openai-chat, which sends both unconditionally and previously failed every request.