[Docs] 吞吐的提升主要是因为重写了GQA的kernel？
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
### 📚 The doc issue
feature里有提到：[2024/04] TurboMind latest upgrade boosts GQA, rocketing the [internlm2-20b](https://huggingface.co/internlm/internlm2-20b) model inference to 16+ RPS, about 1.8x faster than vLLM.
是用fused_multi_head_attention替代了flashattn2的kernel嘛？但是attention也只占整个forward的1/3左右，只是这里的优化能有这么大的收益吗？
### Suggest a potential alternative/fix
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.