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). @ 517676249c8a5e3cb77b52ac69d646ef1ae90939

AlpinDale d7ebffe2f0 chore: re-add the graceful engine shutdown		пре 7 месеци
..
output_processor	f91f217bf8 fix: do not skip `prompt_logprobs` when `SamplingParams.detokenize=True`	пре 7 месеци
__init__.py	04b53d2db5 chore: add initializer files	пре 1 година
aphrodite_engine.py	90ceab32ff refactor: consolidate prompt args to LLM engines	пре 7 месеци
args_tools.py	ec5b99d075 fix: use named args	пре 7 месеци
async_aphrodite.py	d7ebffe2f0 chore: re-add the graceful engine shutdown	пре 7 месеци
metrics.py	fd0a5c0ea4 raise a warning during preemption and swapping	пре 7 месеци