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). @ rc_054

AlpinDale 4d4e767838 ci: take one of fixing lint issues		4 månader sedan
..
benchmarks	4d4e767838 ci: take one of fixing lint issues	4 månader sedan
distributed	7b04361934 fix: support getting `eos_token_id` from the config file	4 månader sedan
endpoints	46159b107a formatting: pt1	6 månader sedan
engine	e42a78381a feat: switch from pylint to ruff (#322)	10 månader sedan
kernels	e1f3fd1e02 fix: test units (#201)	1 år sedan
models	f970f3f3fb add base class for VLMs	5 månader sedan
prompts	e1f3fd1e02 fix: test units (#201)	1 år sedan
samplers	6b1fdd07bd chore: add isort and refactor formatting script and utils	4 månader sedan
tokenization	7b04361934 fix: support getting `eos_token_id` from the config file	4 månader sedan
worker	e1f3fd1e02 fix: test units (#201)	1 år sedan
__init__.py	2755a48d51 merge dev branch into main (#153)	1 år sedan
conftest.py	72229a94da feat: better marlin kernels (#285)	10 månader sedan
test_regression.py	e1f3fd1e02 fix: test units (#201)	1 år sedan