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). @ 172dee25731746a9e8f916ba2d4a8c6b71c16f02

AlpinDale 172dee2573 (2/N) Triton Backend: integrate Triton activation kernels (#1126)		4 giorni fa
..
__init__.py	0c17153073 (1/N) Triton Backend: integrate Triton layernorm kernels (#1125)	5 giorni fa
activation.py	172dee2573 (2/N) Triton Backend: integrate Triton activation kernels (#1126)	4 giorni fa
layernorm.py	172dee2573 (2/N) Triton Backend: integrate Triton activation kernels (#1126)	4 giorni fa
utils.py	172dee2573 (2/N) Triton Backend: integrate Triton activation kernels (#1126)	4 giorni fa