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). @ bitnet

AlpinDale 5884e0b904 add bitnetforcausallm support		il y a 6 mois
..
configs	9e73559eba make use of batched rotary embedding kernels to support long context lora	il y a 6 mois
tokenizer_group	9e73559eba make use of batched rotary embedding kernels to support long context lora	il y a 6 mois
tokenizers	5884e0b904 add bitnetforcausallm support	il y a 6 mois
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	il y a 1 an
config.py	60e74e92fd add rope_scaling arg	il y a 6 mois
detokenizer.py	fca911ee0a vLLM Upstream Sync (#526)	il y a 7 mois
tokenizer.py	5884e0b904 add bitnetforcausallm support	il y a 6 mois