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). @ feat/grok-1

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

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