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). @ 427f6b32fb3f4fd2e12d9d11bf61e93f50620432

AlpinDale 201db10f02 models: add support for Phi3 MoE		1 сар өмнө
..
configs	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
__init__.py	9f3e7c86e2 feat: add fused Marlin MoE kernel (#934)	1 сар өмнө
fused_moe.py	201db10f02 models: add support for Phi3 MoE	1 сар өмнө
layer.py	201db10f02 models: add support for Phi3 MoE	1 сар өмнө
moe_pallas.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө