Skip to content

[Bug] [V1] Try fetching stop_reason from EngineOutput before checking the request #13108

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 12, 2025
Merged

[Bug] [V1] Try fetching stop_reason from EngineOutput before checking the request #13108

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b80a1b6
Try fetching stop_reason from EngineOutput before checking the request
bnellnm Feb 11, 2025
89bad07
review comment, fix type annotation
bnellnm Feb 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions vllm/v1/engine/output_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

import asyncio
from dataclasses import dataclass
from typing import Dict, List, Optional
from typing import Dict, List, Optional, Union

from vllm.outputs import RequestOutput
from vllm.sampling_params import RequestOutputKind
Expand Down Expand Up @@ -164,6 +164,7 @@ def process_outputs(

new_token_ids = engine_core_output.new_token_ids
finish_reason = engine_core_output.finish_reason
stop_reason = engine_core_output.stop_reason

# TODO(andy): prompt logprobs + chunked prefill can
# result in engine core returning an output for a
Expand All @@ -181,9 +182,10 @@ def process_outputs(

# 2) Detokenize the token ids into text and check for stop
# strings.
stop_reason = req_state.detokenizer.update(new_token_ids)
if stop_reason:
stop_string = req_state.detokenizer.update(new_token_ids)
if stop_string and finish_reason != FinishReason.STOP:
finish_reason = FinishReason.STOP
stop_reason = stop_string

# 3) Compute sample and prompt logprobs for request,
# if required.
Expand Down Expand Up @@ -250,7 +252,7 @@ def _make_request_output(
request_state: RequestState,
new_token_ids: List[int],
finish_reason: Optional[FinishReason],
stop_reason: Optional[str],
stop_reason: Union[int, str, None],
) -> Optional[RequestOutput]:

finished = finish_reason is not None
Expand Down