150 citations · 310 across the 71 of their papers we have counts for
8 papers · 1 filter
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…
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…
Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
Yue Guan, Changming Yu, Shihan Fang +8
Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch betwe…
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Cong Guo, Yuxian Qiu, Jingwen Leng +6
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been…
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
Cong Guo, Chen Zhang, Jingwen Leng +5
Quantization is a technique to reduce the computation and memory cost of DNN models, which are getting increasingly large. Existing quantization solutions use fixed-point integer o…
Efficient Adaptive Activation Rounding for Post-Training Quantization
Zhengyi Li, Cong Guo, Zhanda Zhu +5
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method f…
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Cong Guo, Yuxian Qiu, Jingwen Leng +6
Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the o…
Adversarial Defense Through Network Profiling Based Path Extraction
Yuxian Qiu, Jingwen Leng, Cong Guo +4
Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functiona…