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). @ sampling-kernels

AlpinDale 45a004874c chore: allow specifying custom Executor		5 mesi fa
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 mesi fa
cpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
distributed_gpu_executor.py	052a6e1eb6 feat: add SPMD worker execution using Ray accelerated DAG	5 mesi fa
executor_base.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
gpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
multiproc_gpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
multiproc_worker_utils.py	017b42c517 chore: use fork as the default method for mp backend	5 mesi fa
neuron_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
openvino_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
ray_gpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
ray_utils.py	052a6e1eb6 feat: add SPMD worker execution using Ray accelerated DAG	5 mesi fa
ray_xpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
tpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa
xpu_executor.py	45a004874c chore: allow specifying custom Executor	5 mesi fa