5 papers
SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Chung-En Ho, Weiyu Sun, Cheng-Jhih Shih +5
Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch t…
Hardware Acceleration of Block-Diffusion LLM for Edge Devices
Wei-Hsing Huang, Kiseok Lee, Ming-Yen Lee +7
Single-stream (batch-one) edge inference cannot amortize weight traffic across requests. Full-attention diffusion LLMs recompute the entire sequence at every step; native block dif…
BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference
Xiaoyou Wu, Cheng-Jhih Shih, Binfei Ji +2
Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decodin…
A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration
Wei-Hsing Huang, Janak Sharda, Cheng-Jhih Shih +6
Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to b…
3DGauCIM: Accelerating Static/Dynamic 3D Gaussian Splatting via Digital CIM for High Frame Rate Real-Time Edge Rendering
Wei-Hsing Huang, Cheng-Jhih Shih, Jian-Wei Su +10
Dynamic 3D Gaussian splatting (3DGS) extends static 3DGS to render dynamic scenes, enabling AR/VR applications with moving objects. However, implementing dynamic 3DGS on edge devic…