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). @ 58507f4583b1b18d8f8247a875ccefd0ac1133d0

AlpinDale e42a78381a feat: switch from pylint to ruff (#322)		il y a 10 mois
..
README.md	386be46787 fix: megatron-lm url	il y a 1 an
__init__.py	a6a4220fa6 feat: refactor megatron and quants (#57)	il y a 1 an
communication_op.py	4b80b42362 fix: memory leaks due to nccl cuda graphs (#275)	il y a 11 mois
cupy_utils.py	4b80b42362 fix: memory leaks due to nccl cuda graphs (#275)	il y a 11 mois
custom_all_reduce.py	e42a78381a feat: switch from pylint to ruff (#322)	il y a 10 mois
parallel_state.py	e42a78381a feat: switch from pylint to ruff (#322)	il y a 10 mois
utils.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	il y a 1 an

The files here are from the NVIDIA Megatron-LM repository, but only with inference-related code.