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). @ multinode_dynatemp

AlpinDale c9d6f9f164 fix formatting		6 月之前
..
__init__.py	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	10 月之前
cpu_executor.py	fca911ee0a vLLM Upstream Sync (#526)	7 月之前
distributed_gpu_executor.py	c9d6f9f164 fix formatting	6 月之前
executor_base.py	41338053e7 feat: add shutdown method to engine	7 月之前
gpu_executor.py	fca911ee0a vLLM Upstream Sync (#526)	7 月之前
neuron_executor.py	46159b107a formatting: pt1	7 月之前
ray_gpu_executor.py	c21af7acad feat: `DistributedGPUExecutor` abstract class (#541)	6 月之前
ray_utils.py	199e776722 chore: move ray utils to executor dir	7 月之前