collaborators

6 papers

cs.LG2026

QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization

Yipin Guo, Arun M George, Jie Fu +3

Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to ge…

cs.DC2026

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving

Yipin Guo, Siddharth Joshi

Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound de…

cs.RO2024

Efficient Fusion and Task Guided Embedding for End-to-end Autonomous Driving

Yipin Guo, Yilin Lang, Qinyuan Ren

To address the challenges of sensor fusion and safety risk prediction, contemporary closed-loop autonomous driving neural networks leveraging imitation learning typically require a…

cs.LG2024

GPTQT: Quantize Large Language Models Twice to Push the Efficiency

Yipin Guo, Yilin Lang, Qinyuan Ren

Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method,…

cs.LG2024

ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation

Yipin Guo, Zihao Li, Yilin Lang +1

Operators devoid of multiplication, such as Shift and Add, have gained prominence for their compatibility with hardware. However, neural networks (NNs) employing these operators ty…

cs.LG2024

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

Haoran You, Yipin Guo, Yichao Fu +6

Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters…