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). @ 4495b7ab636876d189a20f7d1ee610fac20fbcb3

50h100a 1a5e612eaf pass tensor progress bar as weight iterator		vor 2 Monaten
..
__init__.py	89a2c6dee1 chore: refactor `MultiModalConfig` initialization and profiling (#745)	vor 3 Monaten
loader.py	1a5e612eaf pass tensor progress bar as weight iterator	vor 2 Monaten
neuron.py	0e558e9b2f fix: loading chameleon model with TP>1 (#695)	vor 4 Monaten
openvino.py	0e558e9b2f fix: loading chameleon model with TP>1 (#695)	vor 4 Monaten
tensorizer.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	vor 4 Monaten
utils.py	30d7effc7c feat: add siglip encoder for llava family (#626)	vor 4 Monaten
weight_utils.py	7222b84582 feat: ministral support (#776)	vor 2 Monaten