InternLM / InternLM/InternLM-XComposer
我怎么才能在图灵架构的GPU上部署书生-灵笔2.5大模型？TITAN RTX
Open
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 175
- PR merge metrics
- No merged PRs in 30d
Description
Flash-Attention2报错：FlashAttention only supports Ampere GPUs or newer
一开始选择放弃用这个算法 但是在源代码中发现不可避免地要用这个算法 应该如何解决呢？
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.