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). @ 6785d78d8224bde25e26085e25295d04788582ff

AlpinDale 6785d78d82 fix: do not expose EOS token in the API		há 7 meses atrás
..
output_processor	6785d78d82 fix: do not expose EOS token in the API	há 7 meses atrás
__init__.py	04b53d2db5 chore: add initializer files	há 1 ano atrás
aphrodite_engine.py	90ceab32ff refactor: consolidate prompt args to LLM engines	há 7 meses atrás
args_tools.py	f40b809d3b allow using v2 block manager with sliding window	há 7 meses atrás
async_aphrodite.py	90ceab32ff refactor: consolidate prompt args to LLM engines	há 7 meses atrás
metrics.py	fd0a5c0ea4 raise a warning during preemption and swapping	há 7 meses atrás