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)		пре 2 недеља
..
marlin_kernels	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	пре 2 недеља
align_block_size_kernel.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 5 месеци
marlin_moe_ops.cu	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	пре 2 недеља
marlin_moe_ops.h	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	пре 2 недеља
moe_ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 5 месеци
topk_softmax_kernels.cu	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	пре 2 недеља
torch_bindings.cpp	fa84f8102e kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)	пре 2 недеља