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). @ c154578c97ffda0358f63cd37826655b32de42cc

AlpinDale 29c1b58255 minor logging fixes		7 months ago
..
output_processor	723c6acb84 re-add ngram speculative decoding	7 months ago
__init__.py	04b53d2db5 chore: add initializer files	1 year ago
aphrodite_engine.py	29c1b58255 minor logging fixes	7 months ago
args_tools.py	723c6acb84 re-add ngram speculative decoding	7 months ago
async_aphrodite.py	29c1b58255 minor logging fixes	7 months ago
metrics.py	6fc1ec6e9a fix redirects and improve low level debugging	7 months ago