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). @ control-vectors

AlpinDale ed6717d0c0 feat: initial support for control vectors		4 months ago
..
output_processor	cac8163f77 fix: request abort crashing pipeline parallel	4 months ago
__init__.py	04b53d2db5 chore: add initializer files	1 year ago
aphrodite_engine.py	ed6717d0c0 feat: initial support for control vectors	4 months ago
args_tools.py	ed6717d0c0 feat: initial support for control vectors	4 months ago
async_aphrodite.py	cac8163f77 fix: request abort crashing pipeline parallel	4 months ago
async_timeout.py	3c7444c89b fix: asyncio.run hangs in python < 3.12	5 months ago
metrics.py	fc38c74495 chore: log spec decoding metrics	4 months ago