Skip to content

[Bugfix] Fix Fish Speech and CosyVoice3 online serving - missing is_comprehension and broken model detection #2058

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
hsliuustc0106 merged 2 commits into from
Mar 21, 2026
Merged

[Bugfix] Fix Fish Speech and CosyVoice3 online serving - missing is_comprehension and broken model detection #2058

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
8572a6a
Add missing is_comprehension to Fish Speech and CosyVoice3 stage configs
linyueqian Mar 21, 2026
052e843
Fix _is_fish_speech detection to use engine_args.model_stage
linyueqian Mar 21, 2026
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
3 changes: 2 additions & 1 deletion vllm_omni/entrypoints/openai/serving_speech.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,8 @@ def __init__(self, *args, **kwargs):
self._tts_stage = self._find_tts_stage()
self._is_tts = self._tts_stage is not None
self._is_fish_speech = (
self._tts_stage is not None and getattr(self._tts_stage, "model_stage", None) == "fish_speech_slow_ar"
self._tts_stage is not None
and getattr(getattr(self._tts_stage, "engine_args", None), "model_stage", None) == "fish_speech_slow_ar"
)
self._fish_speech_tokenizer = None

Expand Down
1 change: 1 addition & 0 deletions vllm_omni/model_executor/stage_configs/cosyvoice3.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@

stage_args:
- stage_id: 0
is_comprehension: true

@hsliuustc0106 hsliuustc0106 Mar 21, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

do we have any docs for the arg?

@hsliuustc0106 hsliuustc0106 Mar 21, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

tbh, I do not understand its meaning

runtime:
devices: 0
engine_args:
Expand Down
1 change: 1 addition & 0 deletions vllm_omni/model_executor/stage_configs/fish_speech_s2_pro.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ async_chunk: true
stage_args:
- stage_id: 0
stage_type: llm
is_comprehension: true
runtime:
devices: "0"
max_batch_size: 16
Expand Down
Loading