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).

AlpinDale 9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)		vor 2 Wochen
..
align_block_size_kernel.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
marlin_moe_ops.cu	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	vor 2 Wochen
marlin_moe_ops.h	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	vor 2 Wochen
moe_ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
softmax.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
torch_bindings.cpp	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	vor 2 Wochen