[Infer] Fix transformers streaming logprobs - #9866
Draft
taking-lying-flat wants to merge 1 commit into
Draft
Conversation
taking-lying-flat
force-pushed
the
agent/fix-transformers-stream-logprobs
branch
from
August 6, 2026 14:16
da50411 to
f254d61
Compare
taking-lying-flat
changed the title
taking-lying-flat
force-pushed
the
agent/fix-transformers-stream-logprobs
branch
from
August 7, 2026 00:32
84912a9 to
f254d61
Compare
taking-lying-flat
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
LogitsStreamerinstance used by PT/Transformers generation so streaming responses can consume its logitsRoot cause
The PT streaming path constructed
LogitsStreamer()inline insideLogitsProcessorList, while the locallogits_streamervariable remainedNone. The collection path therefore returned early for every streamed chunk, andlogprobswas serialized asnull.Impact
Requests using the Transformers backend with both
stream=trueandlogprobs=truenow return populated logprobs. Non-streaming inference and streaming requests without logprobs are unchanged.Validation
python -m py_compile swift/infer_engine/transformers_engine.pygit diff --check upstream/main...HEAD