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)		před 5 dny
..
awq_marlin_repack.cu	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	před 1 měsícem
gptq_marlin.cu	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	před 5 dny
gptq_marlin_repack.cu	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	před 5 dny
marlin.cuh	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	před 5 dny
marlin_dtypes.cuh	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	před 5 dny