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_order_v2

AlpinDale e75daadfbd don't copy LogitsProcessors		10 kuukautta sitten
..
common	e75daadfbd don't copy LogitsProcessors	10 kuukautta sitten
endpoints	5638e08d83 Merge branch 'main' into sampler_order_v2	11 kuukautta sitten
engine	e75daadfbd don't copy LogitsProcessors	10 kuukautta sitten
lora	7dc73a779a fix: properly perform garbage collection for lora (#277)	11 kuukautta sitten
modeling	5638e08d83 Merge branch 'main' into sampler_order_v2	11 kuukautta sitten
processing	c0aac15421 feat: S-LoRA support (#222)	1 vuosi sitten
task_handler	697c06c4f5 fix: LoRA support for mixtral (#276)	11 kuukautta sitten
transformers_utils	e31c6f0b45 feat: refactor modeling logic and support more models (#274)	11 kuukautta sitten
__init__.py	3163839c88 bump version to 0.4.9	11 kuukautta sitten
py.typed	1c988a48b2 fix logging and add py.typed	1 vuosi sitten