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). @ c3b15f0926dd24885d9f780f01a451d26fd52653

AlpinDale 3ed4cc431c enc_dec attention code		9 mesi fa
..
layers	3ed4cc431c enc_dec attention code	9 mesi fa
megatron	e42a78381a feat: switch from pylint to ruff (#322)	10 mesi fa
models	a788ca33bf hack in custom bias for attention kernels	9 mesi fa
__init__.py	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	11 mesi fa
hf_downloader.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mesi fa
loader.py	c2d77b1822 chore: logging refactor (#302)	10 mesi fa
metadata.py	58e89e29d9 add custom bias to attention.py	9 mesi fa
outlines_decoding.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mesi fa
outlines_logits_processors.py	e42a78381a feat: switch from pylint to ruff (#322)	10 mesi fa
sampling_metadata.py	9fa99215f8 feat: add cubic sampling (#280)	10 mesi fa
utils.py	2755a48d51 merge dev branch into main (#153)	1 anno fa