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). @ a5bfc2bc3d839e235550c3a13b693bf20422ab39

AlpinDale ea59784f59 tpu: remove torch._dynamo.reset() (#952)		2 meses atrás
..
__init__.py	0e5cf7f840 tpu: avoid dynamo guard eval overhead (#949)	2 meses atrás
test_compilation.py	ea59784f59 tpu: remove torch._dynamo.reset() (#952)	2 meses atrás
test_custom_wrapper.py	0e5cf7f840 tpu: avoid dynamo guard eval overhead (#949)	2 meses atrás