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). @ 205c8e4106a9fc0cdc45102ea11b0eed80a807aa

AlpinDale feb5840f2a feat: async tokenization (#374)		11 hónapja
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 hónapja
executor_base.py	0f6d56b07f feat: model executor refactor (#367)	11 hónapja
gpu_executor.py	0f6d56b07f feat: model executor refactor (#367)	11 hónapja
neuron_executor.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 hónapja
ray_gpu_executor.py	0f6d56b07f feat: model executor refactor (#367)	11 hónapja
utils.py	feb5840f2a feat: async tokenization (#374)	11 hónapja