AlpinDale
|
a985143768
core: add cuda graph support for encoder-decoder models (#1051)
|
4 semanas atrás |
AlpinDale
|
0dfa6b60ec
core: support logprobs with multi-step scheduling (#963)
|
1 mês atrás |
50h100a
|
9576096b9d
iterate over weights normally
|
3 meses atrás |
AlpinDale
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 meses atrás |
AlpinDale
|
a0e446a17d
feat: initial encoder-decoder support with BART model (#633)
|
4 meses atrás |