Skip to content

[BugFix] fix audio end bug #5464

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
ming1753 merged 2 commits into from
Dec 10, 2025
Merged

[BugFix] fix audio end bug #5464

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2fa2b39
[BugFix] fix audio end bug
ming1753 Dec 9, 2025
0d17d6e
fix bug
ming1753 Dec 10, 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
4 changes: 3 additions & 1 deletion fastdeploy/entrypoints/openai/response_processors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,9 @@ async def process_response_chat(self, request_outputs, stream, enable_thinking,
)
yield response
elif decode_type == 2: # audio
if self.eoa_token_id is not None and self.eoa_token_id in token_ids:
if self.eoa_token_id is not None and any(
token_id >= self.eoa_token_id for token_id in token_ids
):
continue
if req_id in self._audio_buffer:
self._audio_buffer[req_id].append(token_ids)
Expand Down
4 changes: 2 additions & 2 deletions tests/entrypoints/openai/test_response_processors.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,9 +60,9 @@ async def test_audio_tts(self):
"""不开启 multimodal，直接走 data_processor"""
processor = ChatResponseProcessor(self.mock_data_processor)
request_outputs = [
{"request_id": "req1", "outputs": {"decode_type": 2, "token_ids": [[11, 22]]}},
{"request_id": "req1", "outputs": {"decode_type": 2, "token_ids": [11, 22]}},
{"request_id": "req1", "outputs": {"decode_type": 0, "token_ids": [1]}},
{"request_id": "req1", "outputs": {"decode_type": 2, "token_ids": [[11, 22]]}},
{"request_id": "req1", "outputs": {"decode_type": 2, "token_ids": [11, 22]}},
{"request_id": "req1", "outputs": {"decode_type": 0, "token_ids": [2]}},
]

Expand Down
Loading