vllm-project/vllm-omni

[Perf]: Voxcpm2 performance improvement

Open

#4,176 opened on Jun 5, 2026

View on GitHub
 (13 comments) (1 reaction) (4 assignees)Python (1,067 forks)github user discovery
good first issuehelp wanted

Repository metrics

Stars
 (4,990 stars)
PR merge metrics
 (PR metrics pending)

Description

VoxCPM2 performance improvement goals:

increase maximum throughput by 10% reduce TTFP under high concurrency by 10%.

Performance optimization directions:

1、Reduce the launch overhead of multi-segment CUDA Graphs. 2、Explore VAE optimization. 3、Analyze performance bottlenecks across different stages on different GPU types.

Current performance metrics：

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Contributor guide

Research direction
Analyze GPU kernel launch overhead for multi segment CUDA graphs and profile VAE inference to identify bottlenecks.
Tech stack
python
Domain
backendmachine learning
Issue type
Performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Python
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30