3 citations · 3 across the 15 of their papers we have counts for
16 papers
PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition
Ziyan Gan, Fangxin Liu, Chenyang Guan +10
Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remai…
Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
Chunyu Qi, Zhuoran Song, Jian Weng +6
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hin…
A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference
Zhuoran Song, Haozhe Jiang, Chunyu Qi +4
Vision-Language-Action (VLA) models have demonstrated strong potential for embodied AI, yet their high inference latency on GPUs limits real-time deployment. Existing accelerators,…
COSM: A Cooperative Scheduling Framework for Concurrent PIM and CPU Execution on Mobile Devices
Yilong Zhao, Fangxin Liu, Onur Mutlu +4
The development of on-device large language models (LLMs) is driven by the need for privacy and fast response times. Energy-intensive data transfer on mobile devices makes Processi…
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
Xuwen Zhou, Fangxin Liu, Chao Wang +5
Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, part…
GEMM-GS: Accelerating 3D Gaussian Splatting on Tensor Cores with GEMM-Compatible Blending
Haomin Li, Bowen Zhu, Fangxin Liu +4
Neural Radiance Fields (NeRF) enables 3D scene reconstruction from several 2D images but incurs high rendering latency via its point-sampling design. 3D Gaussian Splatting (3DGS) i…
HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures
Fangxin Liu, Qinghua Zhang, Hanjing Shen +5
The rapid evolution of Large Language Models (LLMs) towards long-context reasoning and sparse architectures has pushed memory requirements far beyond the capacity of individual dev…
LaMoS: Enabling Efficient Large Number Modular Multiplication through SRAM-based CiM Acceleration
Haomin Li, Fangxin Liu, Chenyang Guan +3
Barrett's algorithm is one of the most widely used methods for performing modular multiplication, a critical nonlinear operation in modern privacy computing techniques such as homo…
SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
Zhixiong Zhao, Fangxin Liu, Junjie Wang +4
The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deployment on end-user devices. In this pape…
QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations
Zhixiong Zhao, Haomin Li, Fangxin Liu +5
Transformer-based models have revolutionized computer vision (CV) and natural language processing (NLP) by achieving state-of-the-art performance across a range of benchmarks. Howe…
PUSHtap: PIM-based In-Memory HTAP with Unified Data Storage Format
Yilong Zhao, Mingyu Gao, Huanchen Zhang +5
Hybrid transaction/analytical processing (HTAP) is an emerging database paradigm that supports both online transaction processing (OLTP) and online analytical processing (OLAP) wor…
FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization
Fangxin Liu, Zongwu Wang, JinHong Xia +6
The rapid advancement of large language models (LLMs) has exacerbated the memory bottleneck due to the widening gap between model parameter scaling and hardware capabilities. While…
LCD: Advancing Extreme Low-Bit Clustering for Large Language Models via Knowledge Distillation
Fangxin Liu, Ning Yang, Junping Zhao +3
Large language models (LLMs) have achieved significant progress in natural language processing but face challenges in deployment due to high memory and computational requirements.…
DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies
Ning Yang, Fangxin Liu, Junjie Wang +4
Large language models (LLMs) have achieved remarkable performance across a wide range of NLP tasks. However, their substantial inference cost poses a major barrier to real-world de…
MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization
Zongwu Wang, Peng Xu, Fangxin Liu +7
Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however,…
ALLMod: Exploring rea-Efficiency of UT-based arge Number ular Reduction via Hybrid Workloads
Fangxin Liu, Haomin Li, Zongwu Wang +5
Modular arithmetic, particularly modular reduction, is widely used in cryptographic applications such as homomorphic encryption (HE) and zero-knowledge proofs (ZKP). High-bit-width…