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). @ profile_no_compile

AlpinDale f7f3fed265 feat: add async postprocessor (#925)		há 1 mês atrás
..
__init__.py	48a8693aed feat: multi-step scheduling (#831)	há 2 meses atrás
test_correctness_async_llm.py	f7f3fed265 feat: add async postprocessor (#925)	há 1 mês atrás
test_correctness_llm.py	b1492c1529 core: add multi-step scheduling support for the synchronous engine (#914)	há 1 mês atrás