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). @ exl2_return

AlpinDale 73177656ed feat: quant_llm support (#755)		3 сар өмнө
..
benchmarks	73177656ed feat: quant_llm support (#755)	3 сар өмнө
distributed	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
endpoints	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
engine	e42a78381a feat: switch from pylint to ruff (#322)	10 сар өмнө
kernels	e1f3fd1e02 fix: test units (#201)	1 жил өмнө
models	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
prompts	e1f3fd1e02 fix: test units (#201)	1 жил өмнө
samplers	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
tokenization	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
worker	e1f3fd1e02 fix: test units (#201)	1 жил өмнө
__init__.py	2755a48d51 merge dev branch into main (#153)	1 жил өмнө
conftest.py	72229a94da feat: better marlin kernels (#285)	10 сар өмнө
test_regression.py	e1f3fd1e02 fix: test units (#201)	1 жил өмнө