Yifu Ding

photo2cartoon-mindspore. MindSpore implementation of GAN-based photo-to-cartoon portrait stylization.

BGEMM-CUDA. BGEMM-CUDA is a CUDA-based low-bit GEMM kernel library for efficient neural network inference. It implements optimized binary and ternary matrix multiplication primitives, including binary-weight and ternary-activation computation, with PyTorch extension support for model-level integration.

Awesome-Edge-LLMs. This is a repository accompanying the survey Edge AI Meets LLM (coming soon), containing a comprehensive list of papers, codebases, toolchains, and open-source frameworks. It is intended to serve as a handbook for researchers and developers interested in Edge/Mobile LLMs.

CyberZY. 赛博周易：模拟最古老的蓍草起卦法。古人选取“蓍草”起卦，用五十根蓍草来摆演出卦象，是取其久远而生生不老之意。今用numpy.random模拟起卦流程，并调用gpt对卦象解卦。纯属娱乐，相信科学！

BUAA_OSLAB. Operating System course lab implementation for BUAA, covering bootstrapping, memory management, drivers, and kernel utilities.

DPTS. Official implementation of Dynamic Parallel Tree Search for accelerating LLM reasoning with test-time parallel search.

Journal-Response-Template. A clean LaTeX template for preparing journal revision responses and reviewer rebuttal letters.

Optimization-Methods-Python. Python implementations of optimization algorithms for Prof. Li Gao's Optimization Methods course assignments at BUAA.

MP-Sparse-Attn. MP-Sparse-Attn provides Triton kernels for Diagonal-Tiled Mixed-Precision Attention, targeting efficient low-bit MXFP inference for Transformer models. It combines tile-level mixed-precision computation and kernel fusion to accelerate attention on modern GPUs.

VocabularyBuilder. An offline iOS vocabulary learning app based on etymology, word roots, and multi-stage practice.