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). @ bitnet

AlpinDale 5b0c11d190 support pipeline parallel pynccl groups		hai 5 meses
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	hai 9 meses
cpu_executor.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	hai 6 meses
distributed_gpu_executor.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	hai 5 meses
executor_base.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	hai 5 meses
gpu_executor.py	236be273e5 feat: tensor parallel speculative decoding (#554)	hai 6 meses
multiproc_gpu_executor.py	5b0c11d190 support pipeline parallel pynccl groups	hai 5 meses
multiproc_worker_utils.py	eaa06fdd14 fix some f-strings	hai 6 meses
neuron_executor.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	hai 6 meses
ray_gpu_executor.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	hai 5 meses
ray_utils.py	c6a501f682 add multiprocessing executor; make ray optional	hai 6 meses