10 papers
AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification
Ji Liu, Puyuan Yang, Rongzhang Zheng +18
High-performance ML systems increasingly rely on GPU kernels whose editable source is unavailable, generated, or too distant from final machine code to expose remaining optimizatio…
Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation
Zekai Li, Ji Liu, Yiqing Huang +3
Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many steps are spent on redundan…
AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents
Sharareh Younesian, Wenwen Ouyang, Sina Rafati +11
GPU kernel optimization is increasingly critical for efficient deep learning systems, but writing high-performance kernels still requires substantial low-level expertise. Recent AI…
Slum Detection and Density Mapping with AlphaEarth Foundations: A Representation Learning Evaluation Across 12 Global Cities
Shuyang Hou, Ziqi Liu, Haoyue Jiao +7
Pixel-level slum mapping has long been constrained by limited cross-city generalisation, the absence of continuous density estimation, and weak global comparability. AlphaEarth Fou…
PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
Zihao An, Taichi Liu, Ziqiong Liu +3
Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target m…
DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
Haowei Zhu, Ji Liu, Ziqiong Liu +4
Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate in…
Learnable Permutation for Structured Sparsity on Transformer Models
Zekai Li, Ji Liu, Guanchen Li +5
Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language mod…
DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation
Jiajun jiao, Haowei Zhu, Puyuan Yang +8
Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhea…
Geak: Introducing Triton Kernel AI Agent & Evaluation Benchmarks
Jianghui Wang, Vinay Joshi, Saptarshi Majumder +7
The demand for AI-generated GPU kernels is rapidly growing, influenced by the need for scalable, hardware-optimized solutions in both industry and academia. As deep learning worklo…
PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
Zihao An, Huajun Bai, Ziqiong Liu +2
The autoregressive nature of large language models (LLMs) fundamentally limits inference speed, as each forward pass generates only a single token and is often bottlenecked by memo…