12 papers
Celty: SpMspV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference
Ruokai Yin, Priyadarshini Panda
Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes…
BRIM: Workload-Balanced Dual-Sided Bit-Serial Sparse Inference Accelerator
Varun Manjunath, Ruokai Yin, Donghyun Lee +2
Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding the speedup. Extending sparsity…
KronQ: LLM Quantization via Kronecker-Factored Hessian
Donghyun Lee, Yuhang Li, Ruokai Yin +1
Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining. Most existing second-order PTQ methods, including GP…
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Donghyun Lee, Jitesh Chavan, Duy Nguyen +5
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training…
Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation
Yuhang Li, Donghyun Lee, Ruokai Yin +1
Low-rank decomposition has emerged as an important problem in Large Language Model (LLM) fine-tuning and inference. Through Singular Value Decomposition (SVD), the weight matrix ca…
Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba
Donghyun Lee, Yuhang Li, Ruokai Yin +2
State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models gro…