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). @ deepseek_v3

AlpinDale ddaefd8d38 chore: remove engine_use_ray (#1024)		il y a 4 semaines
..
output_processor	09dab16f82 core: improve async postproc + multi-step performance (#983)	il y a 1 mois
__init__.py	04b53d2db5 chore: add initializer files	il y a 1 an
aphrodite_engine.py	ddaefd8d38 chore: remove engine_use_ray (#1024)	il y a 4 semaines
args_tools.py	ddaefd8d38 chore: remove engine_use_ray (#1024)	il y a 4 semaines
async_aphrodite.py	ddaefd8d38 chore: remove engine_use_ray (#1024)	il y a 4 semaines
async_timeout.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
metrics.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	il y a 2 mois
metrics_types.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	il y a 2 mois
protocol.py	0dfa6b60ec core: support logprobs with multi-step scheduling (#963)	il y a 1 mois