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). @ rc_054

AlpinDale a3e26391e4 chore: add a wrapper for torch.inference_mode decorator		пре 4 месеци
..
__init__.py	a3e26391e4 chore: add a wrapper for torch.inference_mode decorator	пре 4 месеци
cuda.py	1a40bf438b fix: incorrect gpu capability when used mixed gpus	пре 4 месеци
interface.py	a3e26391e4 chore: add a wrapper for torch.inference_mode decorator	пре 4 месеци
rocm.py	cda0e93a10 abstract away the platform for device capability	пре 4 месеци
tpu.py	a3e26391e4 chore: add a wrapper for torch.inference_mode decorator	пре 4 месеци