[inference]Optimize the usage of intermediate tensors through flash attn #5304
Merged
isky-cd merged 17 commits intohpcaitech:feature/colossal-inferfrom isky-cd:flash_attn_opt_branchJan 26, 2024
+199-57
Commits
Commits on Jan 22, 2024
- committed
Commits on Jan 23, 2024
Commits on Jan 24, 2024
- committed
- committed
- committed
- committed
- committed
Commits on Jan 25, 2024
- committed
- committed
- committed
- committed
- committed
- committed
- committed
- committed
Commits on Jan 26, 2024
- committed