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). @ b20083a1f3b98b136a950671d8c91e6ea4926c44

Stefan Gligorijevic 0feaa6eba8 Merge branch 'main' into samplers-next		1 vuosi sitten
..
__init__.py	07aa2a492f upstream: add option to specify tokenizer	1 vuosi sitten
block.py	5eefbcee26 chore: double-checked the token blocks	1 vuosi sitten
config.py	0495c50a3e GPTQ+exllama support (#21)	1 vuosi sitten
logger.py	4d35c7d936 fix: just because	1 vuosi sitten
logits.py	a86b934469 Fix LogitProcessor infrastructure (#26)	1 vuosi sitten
logits_processor.py	69a4c32b01 fix: openai server (#19)	1 vuosi sitten
outputs.py	45f6d9f923 initial refactor commit	1 vuosi sitten
sampling_params.py	0feaa6eba8 Merge branch 'main' into samplers-next	1 vuosi sitten
sequence.py	75c27d3e65 massive overhaul	1 vuosi sitten
utils.py	75c27d3e65 massive overhaul	1 vuosi sitten