support vLLM >=0.11.0 (V1 engine) for better performance #1640
Conversation
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
Jzz1943
changed the title
ayutaz
pushed a commit
to ayutaz/CosyVoice
that referenced
this pull request
Dec 10, 2025
Upstream improvements from FunAudioLLM/CosyVoice: - PR FunAudioLLM#1640: Support vLLM 0.11.0+ (V1 engine) for better performance - First-chunk latency reduced by ~15ms - More stable latency with smaller fluctuations - Backward compatible with vLLM 0.9.0 - PR FunAudioLLM#1129: Add limited support for MPS devices (Apple Silicon) - Enables partial compatibility with M1/M2/M3/M4 Macs - Auto-enables JIT on MPS for better performance - ONNX models fall back to CPU (ONNX Runtime limitation) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
4 tasks
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Outdated suggestions cannot be applied.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.
Support running CosyVoice2 inference with vLLM 0.11.0(V1 engine only) for better performance.
Under the same conditions, compared with vLLM 0.9.0 (V0 engine), the first-chunk latency for inference with vLLM 0.11.0 (V1 engine) is reduced by approximately 15+ ms. Additionally, the first-chunk latency is more stable, with much smaller fluctuations than the V0 engine.