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 f91991f584 fix: f-string fixes		4 ماه پیش
..
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	11 ماه پیش
fully_sharded_layers.py	8a6e83b52e feat: fully sharded QKVParallelLinearWithLora support	5 ماه پیش
layers.py	99680b2d23 feat: soft prompts (#589)	4 ماه پیش
lora.py	56e0b8223c chore: add base class for LoRA-supported models	5 ماه پیش
models.py	f91991f584 fix: f-string fixes	4 ماه پیش
punica.py	cda0e93a10 abstract away the platform for device capability	4 ماه پیش
request.py	99680b2d23 feat: soft prompts (#589)	4 ماه پیش
utils.py	8a6e83b52e feat: fully sharded QKVParallelLinearWithLora support	5 ماه پیش
worker_manager.py	99680b2d23 feat: soft prompts (#589)	4 ماه پیش