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). @ 53d0ba7c7c33c7668a0b65780f626a470e298872

AlpinDale f7f3fed265 feat: add async postprocessor (#925)		3 mesi fa
..
output_processor	f7f3fed265 feat: add async postprocessor (#925)	3 mesi fa
__init__.py	04b53d2db5 chore: add initializer files	1 anno fa
aphrodite_engine.py	f7f3fed265 feat: add async postprocessor (#925)	3 mesi fa
args_tools.py	f7f3fed265 feat: add async postprocessor (#925)	3 mesi fa
async_aphrodite.py	f7f3fed265 feat: add async postprocessor (#925)	3 mesi fa
async_timeout.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 mesi fa
metrics.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	4 mesi fa
metrics_types.py	3d83e64f8e feat: add metrics for prefix cache hit rate (#829)	4 mesi fa
protocol.py	b5aa11020b api: fix crashes under very high loads (#878)	3 mesi fa