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). @ 156f577f79c2751cabc9b823696ace6d029371d7

AlpinDale 17eb1b7eb9 chore: remove ray health check		7 months ago
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 months ago
cpu_executor.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	7 months ago
distributed_gpu_executor.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
executor_base.py	de62ceb18c refactor: eliminate parallel worker per-step task scheduling overhead	7 months ago
gpu_executor.py	236be273e5 feat: tensor parallel speculative decoding (#554)	7 months ago
multiproc_gpu_executor.py	05d6e43244 fix: `torch.compile()` with mp executor backend	7 months ago
multiproc_worker_utils.py	eaa06fdd14 fix some f-strings	7 months ago
neuron_executor.py	ef733aee43 implement ExecuteModelData to reduce executor complexity	7 months ago
ray_gpu_executor.py	17eb1b7eb9 chore: remove ray health check	7 months ago
ray_utils.py	c6a501f682 add multiprocessing executor; make ray optional	7 months ago