david/aphrodite-engine

mirror de https://github.com/PygmalionAI/aphrodite-engine

Autor	SHA1 Mensagem	Data
AlpinDale	a20e2ce155 fix: pass cutlass_fp8_supported correctly for fbgemm_fp8	há 5 meses atrás
AlpinDale	598afb63dd chore: add ignored layers for fp8 quant	há 5 meses atrás
AlpinDale	32acf54c63 fix: fbgemm_fp8 when modules_to_not_convert=None	há 5 meses atrás
AlpinDale	408ca43d2e feat: support fbgemm_fp8 quant on ampere	há 5 meses atrás
AlpinDale	9be43994fe feat: fbgemm quantization support (#601)	há 5 meses atrás