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). @ 651678d2dfadc32b58f8a48160c22184d5a48a17

AlpinDale 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)		пре 3 месеци
..
align_block_size_kernel.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
marlin_moe_ops.cu	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	пре 3 месеци
marlin_moe_ops.h	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	пре 3 месеци
moe_ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
softmax.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
torch_bindings.cpp	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	пре 3 месеци