5 papers
Accuracy-Configurable Floating-Point Multiplier Design for SRAM-Based Compute-in-Memory
Yiqi Zhou, Junhao Lu, Jiale Yu +5
Digital Compute-in-Memory (DCiM) reduces data movement and has become a promising solution for energy-efficient edge AI. However, most existing DCiM frameworks still primarily targ…
OpenACMv2: An Accuracy-Constrained Co-Optimization Framework for Approximate DCiM
Yiqi Zhou, Yue Yuan, Yikai Wang +8
Digital Compute-in-Memory (DCiM) accelerates neural networks by reducing data movement. Approximate DCiM can further improve power-performance-area (PPA), but demands accuracy-cons…
X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms
Yueming Yuan, Ahan Gupta, Jianping Li +3
Emerging expert-specialized Mixture-of-Experts (MoE) architectures, such as DeepSeek-MoE, deliver strong model quality through fine-grained expert segmentation and large top-k rout…
MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
Beichen Huang, Yueming Yuan, Zelei Shao +1
A critical approach for efficiently deploying Mixture-of-Experts (MoE) models with massive parameters is quantization. However, state-of-the-art MoE models suffer from non-negligib…
SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention
Ahan Gupta, Yueming Yuan, Devansh Jain +4
Multi-head-self-attention (MHSA) mechanisms achieve state-of-the-art (SOTA) performance across natural language processing and vision tasks. However, their quadratic dependence on…