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/jamba-support

AlpinDale 4fbb052b34 add jamba config file		vor 8 Monaten
..
configs	4fbb052b34 add jamba config file	vor 8 Monaten
tokenizer_group	282d7b7f9c fix multi-gpu ray tokenizer for trust_remote_code	vor 9 Monaten
tokenizers	da223153c6 feat&fix: cohere support and missing GPU blocks (#333)	vor 9 Monaten
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	vor 1 Jahr
config.py	4fbb052b34 add jamba config file	vor 8 Monaten
detokenizer.py	c18bf116da fix stop strings not being excluded from outputs	vor 9 Monaten
tokenizer.py	aa1db50131 simplify tokenizer.py	vor 9 Monaten