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