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		5 сар өмнө
..
configs	9e73559eba make use of batched rotary embedding kernels to support long context lora	5 сар өмнө
tokenizer_group	9e73559eba make use of batched rotary embedding kernels to support long context lora	5 сар өмнө
tokenizers	5884e0b904 add bitnetforcausallm support	5 сар өмнө
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	1 жил өмнө
config.py	60e74e92fd add rope_scaling arg	5 сар өмнө
detokenizer.py	fca911ee0a vLLM Upstream Sync (#526)	6 сар өмнө
tokenizer.py	5884e0b904 add bitnetforcausallm support	5 сар өмнө