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). @ feat/jamba-support

AlpinDale a1f18f17e6 modify the cache engine and model runner/worker to support mamba states		9 miesięcy temu
..
__init__.py	04b53d2db5 chore: add initializer files	1 rok temu
aphrodite_engine.py	a1f18f17e6 modify the cache engine and model runner/worker to support mamba states	9 miesięcy temu
args_tools.py	bd0ddf1cfe feat: EETQ quantization (#408)	9 miesięcy temu
async_aphrodite.py	9aaeb5d349 add speculative config and arg for later	9 miesięcy temu
metrics.py	b1caee23a6 cache the p2p access check for memory saving	9 miesięcy temu
ray_tools.py	8c9cabf4c8 fix: display error in ray before deadlock (#378)	10 miesięcy temu