Learning Modern 3D Graphics Programming

Connecting cheap digital calipers to Raspberry Pi and decode readings

Jekyll project powering seb-v.github.io

CUDA accelerated rasterization of gaussian splatting

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

SGLang is a fast serving framework for large language models and vision language models.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Fully open reproduction of DeepSeek-R1

The ultimate Python binding for Vulkan API

A utility for building graphics API layer drivers, and a some off-the-shelf layers for the Arm Immortalis and Arm Mali GPUs.

Tutorial for the Vulkan graphics and compute API

Understanding the interplay between memorization and generalization in neural networks, featuring MAT, a learning algorithm to enhance robustness by mitigating spurious correlations.

BARVINN: A Barrel RISC-V Neural Network Accelerator: https://barvinn.readthedocs.io/en/latest/

Official inference framework for 1-bit LLMs

Stack trace visualizer

The fastest way to create an HTML app

The Tensor (or Array)

A serial device I/O tool

The Autograd Engine

Discovering environments with XRM

The n-gram Language Model

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing

VCD viewer

🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.

Codebase for the ECCV 2024 paper: Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance

Nvidia Instruction Set Specification Generator

UNet diffusion model in pure CUDA

High-efficiency floating-point neural network inference operators for mobile, server, and Web

LLM101n: Let's build a Storyteller