From the 1 of 11 linked papers with an AI index.
11 papers
GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design
Yitong Ding, Jiawei Huang, Renyang Guan +7
The paper introduces GPU‑Tile‑Sim, a tile‑centric GPU simulation framework that models LLM kernels using warp‑level tile graphs to capture dependency and overlap, achieving low err…
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
Xinwei Qiang, Yifan Hu, Shixuan Sun +6
Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each…
CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
Xing Ma, Yangjie Zhou, Wu Sun +6
Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Exi…
InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
Hongyu Chen, Letian Ruan, Zilin Xu +6
LoRA enables efficient customization of LLMs and is widely used in multi-tenant and multi-task serving. However, emerging model architectures such as MoE significantly increase LoR…
Towards High-Goodput LLM Serving with Prefill-decode Multiplexing
Yukang Chen, Weihao Cui, Han Zhao +7
Large Language Model (LLM) serving must meet stringent Service Level Objectives (SLOs) for both the prefill and decode phases. Some existing solutions disaggregate the two phases,…
DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training
Xinwei Qiang, Hongmin Chen, Shixuan Sun +3
Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In widely used attention implementations such…