inference-acceleration topic

⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.

autonomi-ai

[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising

czg1225

This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"

dvlab-research

Implementation of ICCV 2025 paper "Growing a Twig to Accelerate Large Vision-Language Models".

MILVLG

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

ali-vilab