david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ 5b0c11d190642d95c26c511fe1499b5a5cbda77c

AlpinDale f6250c5516 move dockerfiles to root; fix cpu build		7 ヶ月前
..
backends	f6250c5516 move dockerfiles to root; fix cpu build	7 ヶ月前
ops	8e11259e90 missing triton autoconfig for rocm flash attn	7 ヶ月前
__init__.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	7 ヶ月前
layer.py	656459fd84 make fp8_e4m3 work on nvidia	7 ヶ月前
selector.py	19a959a03e prioritize user selection for attention	7 ヶ月前