Stars
Local-only macOS bridge for personally copied Wallpaper Engine Workshop wallpapers
A unified inference and post-training framework for accelerated video generation.
A Datacenter Scale Distributed Inference Serving Framework
[ICLR 2026] ParoQuant: Pairwise Rotation Quantization 4C36 for Efficient Reasoning LLM Inference
[ECCV 2026] Official implementation of "MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens"
SGLang is a high-performance serving framework for large language models and multimodal models.
2022-2 capstone design 'Lincall'