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). @ seqdata-factor

AlpinDale 960dee2f97 torch.compile: fix functionalization (#1045)		4 nedēļas atpakaļ
..
__init__.py	0e5cf7f840 tpu: avoid dynamo guard eval overhead (#949)	1 mēnesi atpakaļ
backends.py	960dee2f97 torch.compile: fix functionalization (#1045)	4 nedēļas atpakaļ
wrapper.py	0e5cf7f840 tpu: avoid dynamo guard eval overhead (#949)	1 mēnesi atpakaļ