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). @ rc_054

AlpinDale 4d4e767838 ci: take one of fixing lint issues		6 сар өмнө
..
aqlm.py	5dbfc200f2 update all benchmarks (#597)	7 сар өмнө
benchmark_shapes.py	5dbfc200f2 update all benchmarks (#597)	7 сар өмнө
marlin.py	4d4e767838 ci: take one of fixing lint issues	6 сар өмнө
moe.py	5dbfc200f2 update all benchmarks (#597)	7 сар өмнө
paged_attention.py	5dbfc200f2 update all benchmarks (#597)	7 сар өмнө
rope.py	5dbfc200f2 update all benchmarks (#597)	7 сар өмнө