[Feature] 当前qwen-next等SSM类模型prefix cache缓存命中率低
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### Motivation
对于qwen-next等SSM类模型，pytorch backend在启动prefix cache时难以命中缓存
#4859
### Related resources
_No response_
### Additional context
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.