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). @ dynatempagain

AlpinDale f1d0b77c92 [0.6.0] Release Candidate (#481)		4 months ago
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 months ago
cpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
distributed_gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
executor_base.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
multiproc_gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
multiproc_worker_utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
neuron_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
openvino_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
ray_gpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
ray_tpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
ray_utils.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
ray_xpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
tpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago
xpu_executor.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 months ago