2 citations · 3 across the 10 of their papers we have counts for
11 papers
DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding
Junqing Lin, Jingwei Sun, Guangzhong Sun
Linear attention models eliminate the quadratic prefix computation and context-growing KV cache of softmax attention by replacing pairwise token interactions with recurrent state u…
FlashQuant: Sparse-Dense Fusion for Memory-Efficient Outlier-Aware LLM Inference
Junqing Lin, Jingwei Sun, Zhengding Hu +1
Low-bit quantization reduces the memory footprint and computational cost of large language model (LLM) inference. However, high-magnitude outlier weights can induce substantial qua…
EMO: Energy Efficiency Modeling and Optimization for AI Workloads
Jiyu Luo, Shaoyu Chen, Jingwei Sun +3
The massive energy consumption of GPU-accelerated AI workloads challenges sustainable computing. We observe that execution asynchrony (e.g., CPU-GPU, concurrent streams, multi-GPU)…
GCL-Sampler: Discovering Kernel Similarity for Sampled GPU Simulation via Graph Contrastive Learning
Jiaqi Wang, Jingwei Sun, Jiyu Luo +2
GPU architectural simulation is orders of magnitude slower than native execution, necessitating workload sampling for practical speedups. Existing methods rely on hand-crafted feat…
RSH-SpMM: A Row-Structured Hybrid Kernel for Sparse Matrix-Matrix Multiplication on GPUs
Aiying Li, Jingwei Sun, Han Li +2
Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental computation in graph analytics, scientific simulation, and sparse deep learning workloads. However, the extreme irregula…
Token Pruning for In-Context Generation in Diffusion Transformers
Junqing Lin, Xingyu Zheng, Pei Cheng +3
In-context generation significantly enhances Diffusion Transformers (DiTs) by enabling controllable image-to-image generation through reference examples. However, the resulting inp…
Toward Efficient SpMV in Sparse LLMs via Block Extraction and Compressed Storage
Junqing Lin, Jingwei Sun, Mingge Lu +1
Sparse Matrix-Vector Multiplication (SpMV) has become a critical performance bottleneck in the local deployment of sparse Large Language Models (LLMs), where inference predominantl…
FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data
Hao Sun, Li Shen, Shixiang Chen +4
Federated learning is an emerging distributed machine learning method, enables a large number of clients to train a model without exchanging their local data. The time cost of comm…
AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks
Hao Sun, Li Shen, Qihuang Zhong +6
Sharpness aware minimization (SAM) optimizer has been extensively explored as it can generalize better for training deep neural networks via introducing extra perturbation steps to…
Synthesizing Proxy Applications for MPI Programs
Jiyu Luo, Tao Yan, Qingguo Xu +2
Proxy applications (proxy-apps) are basic tools for evaluating the performance of specific workloads on high-performance computing (HPC) systems. Since the development of high-fide…
Robust Quantity-Aware Aggregation for Federated Learning
Jingwei Yi, Fangzhao Wu, Huishuai Zhang +4
Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning fram…