4 papers
SwiftFusion: Scalable Sequence Parallelism for Distributed Inference of Diffusion Transformers on GPUs
Jiacheng Yang, Jun Wu, Yaoyao Ding +3
Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single…
UCCL-Zip: Lossless Compression Supercharged GPU Communication
Shuang Ma, Chon Lam Lao, Zhiying Xu +8
The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compressi…
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving
Xinyu Wang, Jonas M. Kübler, Kailash Budhathoki +2
When serving a single base LLM with several different LoRA adapters simultaneously, the adapters cannot simply be merged with the base model's weights as the adapter swapping would…
Tilus: A Tile-Level GPGPU Programming Language for Low-Precision Computation
Yaoyao Ding, Bohan Hou, Xiao Zhang +5
Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational…