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). @ sampler_refactor

AlpinDale 737f1c3351 part 1		6 kuukautta sitten
..
attention	46159b107a formatting: pt1	6 kuukautta sitten
common	737f1c3351 part 1	6 kuukautta sitten
distributed	d1a3c7bc2c chore: simplify try-finally logic in pynccl	6 kuukautta sitten
endpoints	46159b107a formatting: pt1	6 kuukautta sitten
engine	737f1c3351 part 1	6 kuukautta sitten
executor	41338053e7 feat: add shutdown method to engine	6 kuukautta sitten
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	10 kuukautta sitten
lora	8be299e78b fix: lora load check	7 kuukautta sitten
modeling	737f1c3351 part 1	6 kuukautta sitten
processing	737f1c3351 part 1	6 kuukautta sitten
quantization	46159b107a formatting: pt1	6 kuukautta sitten
spec_decode	9d81716bfd [v0.5.3] Release Candidate (#388)	8 kuukautta sitten
task_handler	2e0b115ce1 move func tracing to utils	6 kuukautta sitten
transformers_utils	ed759f065d chore: tokenizer_revision -> revision	6 kuukautta sitten
__init__.py	199e776722 chore: move ray utils to executor dir	6 kuukautta sitten
py.typed	1c988a48b2 fix logging and add py.typed	1 vuosi sitten