A unified inference runtime for VLA models.

美股指南

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Nano vLLM

📚《统计学习方法-李航: 笔记》 200页PDF，公式细节讲解🎉

Lattice Sieving using GPU Tensor cores based on the General Sieve Kernel (G6K)

The General Sieve Kernel

Lattice algorithms using floating-point arithmetic

A Python interface for https://github.com/fplll/fplll

GPGPU processor supporting RISCV-V extension, developed with Chisel HDL

Summary, Code for Deep Neural Network Quantization

Implementation of the Optimal Brain Damage paper in PyTorch (using second order Taylor series to prune neural networks)

一生一芯RISCV处理器核代码仓库（包括相关工具）

A terminal for a more modern age

collection of benchmarks to measure basic GPU capabilities

A massively parallel, high-level programming language

The Mojo Programming Language

learning how CUDA works

stb single-file public domain libraries for C/C++

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Java, C++, Python, Go, JS, TS, C#, Swift, Rust, Dart, Zig 等语言。

高性能并行编程与优化 - 课件

BY Blog ->

科技爱好者周刊，每周五发布

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!