Auteur | SHA1 Message | Date |
---|---|---|
|
656459fd84 make fp8_e4m3 work on nvidia | il y a 6 mois |
|
50b7c13db0 refactor: attention selector (#552) | il y a 6 mois |
|
b178ae4b4a chore: generalize linear_method to be quant_method (#540) | il y a 6 mois |
|
fca911ee0a vLLM Upstream Sync (#526) | il y a 7 mois |