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). @ 5b0c11d190642d95c26c511fe1499b5a5cbda77c

AlpinDale 5b0c11d190 support pipeline parallel pynccl groups		hai 8 meses
..
__init__.py	2bd6c92f73 fix: lora inclusion in wheels	hai 1 ano
fully_sharded_layers.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 8 meses
layers.py	9e73559eba make use of batched rotary embedding kernels to support long context lora	hai 8 meses
lora.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 8 meses
models.py	9e73559eba make use of batched rotary embedding kernels to support long context lora	hai 8 meses
punica.py	e87c32bed3 feat: full tensor parallel for LoRA layers (#545)	hai 8 meses
request.py	5b0c11d190 support pipeline parallel pynccl groups	hai 8 meses
utils.py	9e73559eba make use of batched rotary embedding kernels to support long context lora	hai 8 meses
worker_manager.py	9e73559eba make use of batched rotary embedding kernels to support long context lora	hai 8 meses