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). @ fp8-quant

AlpinDale c20073824a cleanup		7 bulan lalu
..
attention	66b7bc4415 sliding window in prefix kernel	7 bulan lalu
common	42998e423c better quant verification	7 bulan lalu
distributed	096d9eb6c5 enhance nvlink detection	7 bulan lalu
endpoints	fb7825df8f squash logprobs	7 bulan lalu
engine	42998e423c better quant verification	7 bulan lalu
executor	f894f7b176 Revert "reduce dedupe by wrapping in general worker class"	7 bulan lalu
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	10 bulan lalu
lora	8be299e78b fix: lora load check	7 bulan lalu
modeling	85a865cc00 feat: fp8 quant	7 bulan lalu
processing	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
quantization	c20073824a cleanup	7 bulan lalu
spec_decode	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
task_handler	f894f7b176 Revert "reduce dedupe by wrapping in general worker class"	7 bulan lalu
transformers_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 bulan lalu
py.typed	1c988a48b2 fix logging and add py.typed	1 tahun lalu