Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
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…
cs.LG2025
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…