 AlpinDale
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
1 mese fa |
|
AlpinDale
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
4 mesi fa |
|
AlpinDale
|
60b702a827
chore: register custom torch ops for flash-attn and flashinfer (#724)
|
4 mesi fa |
|
AlpinDale
|
24456206a9
fix: logit softcapping in flash-attn (#688)
|
4 mesi fa |
|
AlpinDale
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
4 mesi fa |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 mesi fa |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 mesi fa |
