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). @ multinode_dynatemp

AlpinDale c2be1b9f29 formatting		vor 5 Monaten
..
attention	0d3562a7f9 MQA in triton FA	vor 5 Monaten
common	3ab36e6b2d feat: extended RoPE for Llama 3.1 (#543)	vor 5 Monaten
distributed	d1a3c7bc2c chore: simplify try-finally logic in pynccl	vor 6 Monaten
endpoints	46159b107a formatting: pt1	vor 6 Monaten
engine	aed64884c6 feat: prompt logprobs with chunked prefill (#539)	vor 5 Monaten
executor	c9d6f9f164 fix formatting	vor 5 Monaten
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	vor 10 Monaten
lora	b178ae4b4a chore: generalize linear_method to be quant_method (#540)	vor 5 Monaten
modeling	c2be1b9f29 formatting	vor 5 Monaten
processing	aed64884c6 feat: prompt logprobs with chunked prefill (#539)	vor 5 Monaten
quantization	36660b55c2 chore: mixtral fp8 w/ static scales (#542)	vor 5 Monaten
spec_decode	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 8 Monaten
task_handler	aed64884c6 feat: prompt logprobs with chunked prefill (#539)	vor 5 Monaten
transformers_utils	ed759f065d chore: tokenizer_revision -> revision	vor 6 Monaten
__init__.py	199e776722 chore: move ray utils to executor dir	vor 6 Monaten
py.typed	1c988a48b2 fix logging and add py.typed	vor 1 Jahr