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/gumbell-softmax-experiment

AlpinDale 15a0454172 feat: FP8 KV Cache (#185)		hai 1 ano
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	hai 1 ano
block.py	74604eb252 fix: pylint complaints (#91)	hai 1 ano
config.py	15a0454172 feat: FP8 KV Cache (#185)	hai 1 ano
logger.py	8834ecf9de chore: clean up refactor endpoints (#98)	hai 1 ano
logits_processor.py	f013d714c0 chore: merge dev branch into main (#177)	hai 1 ano
outputs.py	efc6f7fbec chore: reformats (#90)	hai 1 ano
sampling_params.py	f013d714c0 chore: merge dev branch into main (#177)	hai 1 ano
sequence.py	f013d714c0 chore: merge dev branch into main (#177)	hai 1 ano
utils.py	f013d714c0 chore: merge dev branch into main (#177)	hai 1 ano