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). @ 72cd8494aadb5eb1a3064ccd3437bd8814c51d38

AlpinDale 0f6d56b07f feat: model executor refactor (#367)		há 11 meses atrás
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	há 11 meses atrás
executor_base.py	0f6d56b07f feat: model executor refactor (#367)	há 11 meses atrás
gpu_executor.py	0f6d56b07f feat: model executor refactor (#367)	há 11 meses atrás
neuron_executor.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	há 11 meses atrás
ray_gpu_executor.py	0f6d56b07f feat: model executor refactor (#367)	há 11 meses atrás
utils.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	há 11 meses atrás