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). @ 78de98463ba6956b51a2bb16daab90cbe2d1d645

AlpinDale 9d81716bfd [v0.5.3] Release Candidate (#388)		há 10 meses atrás
..
align_block_size_kernel.cu	9d81716bfd [v0.5.3] Release Candidate (#388)	há 10 meses atrás
moe_ops.cpp	7d6ba53602 feat: fused top-k kernels for MoE (#273)	há 1 ano atrás
moe_ops.h	7d6ba53602 feat: fused top-k kernels for MoE (#273)	há 1 ano atrás
softmax.cu	9d81716bfd [v0.5.3] Release Candidate (#388)	há 10 meses atrás