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 7fffa507ff build: build flash attention kernels inside aphrodite (#1085)		2 nedēļas atpakaļ
..
backends	7fffa507ff build: build flash attention kernels inside aphrodite (#1085)	2 nedēļas atpakaļ
ops	7fffa507ff build: build flash attention kernels inside aphrodite (#1085)	2 nedēļas atpakaļ
__init__.py	1405051912 attention: add `AttentionState` abstraction (#863)	2 mēneši atpakaļ
layer.py	bf88c8567e feat: mamba model support (#674)	5 mēneši atpakaļ
selector.py	7fffa507ff build: build flash attention kernels inside aphrodite (#1085)	2 nedēļas atpakaļ