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). @ get_last_latency_hack

AlpinDale 132aa2abe4 spec decode: add support for EAGLE (#899)		hai 1 mes
..
configs	132aa2abe4 spec decode: add support for EAGLE (#899)	hai 1 mes
tokenizer_group	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
tokenizers	fb96041ae3 fix: demote skip_special_tokens assertion to logger error (#778)	hai 3 meses
__init__.py	267c73c5d3 chore: minor tokenizer tweaks	hai 1 ano
config.py	132aa2abe4 spec decode: add support for EAGLE (#899)	hai 1 mes
detokenizer.py	4648f16c84 chore: fix return statement in Detokenizer class (#727)	hai 4 meses
image_processor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses
tokenizer.py	d5033e12fd feat: implement mistral tokenizer mode (#711)	hai 4 meses
utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hai 4 meses