4 papers
PADE: A Predictor-Free Sparse Attention Accelerator via Unified Execution and Stage Fusion
Huizheng Wang, Hongbin Wang, Zichuan Wang +5
Attention-based models have revolutionized AI, but the quadratic cost of self-attention incurs severe computational and memory overhead. Sparse attention methods alleviate this by…
From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing
Yushu Zhao, Yubin Qin, Yang Wang +5
Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model si…
MoBiLE: Efficient Mixture-of-Experts Inference on Consumer GPU with Mixture of Big Little Experts
Yushu Zhao, Yubin Qin, Yang Wang +5
Mixture-of-Experts (MoE) models have recently demonstrated exceptional performance across a diverse range of applications. The principle of sparse activation in MoE models facilita…
MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness
Huizheng Wang, Zichuan Wang, Zhiheng Yue +8
Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. Thi…