Remake of the original Super Mario Bros game.

Learning in infinite dimension with neural operators.

本人的科研经验

A repo for llm on ncnn

A linear algebra library for the Zig programming language

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

An intuitive and low-overhead instrumentation tool for Python

Pytorch implementation for MeanFlow

Variational Monte-Carlo updated PEPS

JAX implementation of MeanFlow

Ongoing research training transformer models at scale

VideoNSA: Native Sparse Attention Scales Video Understanding

A library of GPU kernels for sparse matrix operations.

Speedup the attention computation of Swin Transformer

A tiny deep learning training framework implemented from scratch in C++ that follows PyTorch's API.

A really tiny autograd engine

LeetGPU Solutions

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Fast and memory-efficient exact attention

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

CUDA Kernel Benchmarking Library

generation of training-optimised weather datasets from declarative syntax