Hi my new friend!

书山有路勤为径，
学海无涯苦作舟。

Home
page

Scroll down

Welcome to Zongwu's Science Hub ✨

Residence:

Shanghai
Age:

18

Architecture 187

System 45

Newest Publications

PCcheck_ Persistent Concurrent Checkpointing for ML

26/03/27
10:27

TurboQuant_ Online Vector Quantization with Near-optimal Distortion Rate

26/03/26
10:32

LUT Tensor Core_ A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference

26/03/25
11:09

KV Cache is 1 Bit Per Channel_ Efficient Large Language Model Inference with Coupled Quantization

26/03/24
18:51

T-MAC_ CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge

26/03/24
16:30

FIGLUT_ An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables

26/03/24
14:59

QuIP-sharp_Even_Better_LLM_Quantization_with_Hadamard_Incoherence_and_Lattice_Codebooks

26/03/24
14:03

LUT-DLA_ Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator

26/03/24
12:56

Flash-KMeans_ Fast and Memory-Efficient Exact K-Means

26/03/24
11:11

PD-Swap_ Prefill-Decode Logic Swapping for End-to-End LLM Inference on Edge FPGAs via Dynamic Partial Reconfiguration

26/03/23
17:20

1 2 345 6…28