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). @ 172dee25731746a9e8f916ba2d4a8c6b71c16f02

AlpinDale fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)		6 өдөр өмнө
..
configs	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 сар өмнө
__init__.py	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	6 өдөр өмнө
fused_marlin_moe.py	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	6 өдөр өмнө
fused_moe.py	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	6 өдөр өмнө
layer.py	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	6 өдөр өмнө
moe_pallas.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	5 сар өмнө