AlpinDale
|
0f4a9ee77b
quantized lm_head (#582)
|
5 月之前 |
AlpinDale
|
ae04f57ec1
feat: Pipeline Parallel support (#581)
|
5 月之前 |
AlpinDale
|
656459fd84
make fp8_e4m3 work on nvidia
|
6 月之前 |
AlpinDale
|
50b7c13db0
refactor: attention selector (#552)
|
6 月之前 |
AlpinDale
|
1e35cef979
feat: add arctic snowflake model (#551)
|
6 月之前 |