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). @ 5b0c11d190642d95c26c511fe1499b5a5cbda77c

AlpinDale 5b0c11d190 support pipeline parallel pynccl groups		7 months ago
..
output_processor	5b0c11d190 support pipeline parallel pynccl groups	7 months ago
__init__.py	04b53d2db5 chore: add initializer files	1 year ago
aphrodite_engine.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
args_tools.py	f6250c5516 move dockerfiles to root; fix cpu build	7 months ago
async_aphrodite.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
metrics.py	fd0a5c0ea4 raise a warning during preemption and swapping	7 months ago