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). @ feat/tree-attention

AlpinDale c577c31aaa feat: tree attention		il y a 9 mois
..
output_processor	c577c31aaa feat: tree attention	il y a 9 mois
__init__.py	04b53d2db5 chore: add initializer files	il y a 1 an
aphrodite_engine.py	a3b1602391 fix: rope scaling for cohere and qwen (#436)	il y a 9 mois
args_tools.py	60ca1e1e5e feat: add ngram prompt lookup decoding for speculative decoding (#438)	il y a 9 mois
async_aphrodite.py	f216601f18 fix: logging in the API server	il y a 9 mois
metrics.py	d8c4193704 feat: Speculative Decoding using a draft model (#432)	il y a 9 mois
ray_tools.py	8c9cabf4c8 fix: display error in ray before deadlock (#378)	il y a 10 mois