nano-vllm-voxcpm问题反馈
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 37.8k
- Forks
- 4.3k
- Avg merge
- 7m
- Merged PRs (30d)
- 1
Description
我们尝试用nano-vllm-voxcpm部署流式推理，对比原生流式推理，结果如下：
1）中间包nano-vllm-voxcpm推理速度【22ms】比原生推理【45ms】快一倍左右；
2）首包nano-vllm-voxcpm推理速度【189ms】比原生推理【147ms】慢一些；
请问有办法提高 nano-vllm-voxcpm 在流式推理时首包的生成速度吗？
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the reported streaming benchmark, comparing first-packet latency with intermediate-packet latency for nano-vllm-voxcpm and native inference. Trace the streaming inference entry point and measure the first-packet path; done means reducing the reported 189 ms first-packet latency without regressing intermediate-packet speed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning, performance
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100