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). @ 7d0884de9ab1b8cb0a8cd7578bd0c6a7ef7f02f4

AlpinDale 5b0c11d190 support pipeline parallel pynccl groups		8 月之前
..
output_processor	5b0c11d190 support pipeline parallel pynccl groups	8 月之前
__init__.py	04b53d2db5 chore: add initializer files	1 年之前
aphrodite_engine.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	8 月之前
args_tools.py	f6250c5516 move dockerfiles to root; fix cpu build	8 月之前
async_aphrodite.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	8 月之前
metrics.py	fd0a5c0ea4 raise a warning during preemption and swapping	8 月之前