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). @ 349a6123387f79441e91473715b7e2e9db768e52

AlpinDale 6b75a66c60 fix: unsafe all-reduce sync (#1118)		1 month ago
..
custom_all_reduce.cu	239a8cae25 torch.compile: register all-reduce operations as custom ops (#1050)	2 months ago
custom_all_reduce.cuh	6b75a66c60 fix: unsafe all-reduce sync (#1118)	1 month ago
custom_all_reduce_test.cu	6b75a66c60 fix: unsafe all-reduce sync (#1118)	1 month ago