《数学建模导论》教程，全网最全数学建模模型与算法教程系列，带你走进数学建模的大门！

A Quirky Assortment of CuTe Kernels

Production-grade client-side tracing, profiling, and analysis for complex software systems.

Python tool for converting files and office documents to Markdown.

Puzzles for learning Triton, play it with minimal environment configuration!

EFFICIENT AND OPTIMIZED TOKENIZER ENGINE FOR LLM INFERENCE SERVING

#1 Locally hosted web application that allows you to perform various operations on PDF files

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

Performance benchmark framework for C++ with nanoseconds measure precision

A command-line benchmarking tool

From Minimal GEMM to Everything

青稞Talk

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems

SGLang kernel library for NPU

NumPy & SciPy for GPU

An animation engine implemented in rust, inspired by manim and JAnim

Deep learning at the speed of light.

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

GlibC Malloc for Exploiters presentation

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

MPI programming lessons in C and executable code examples

CUDA on non-NVIDIA GPUs

Nano vLLM

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

LiteRT continues the legacy of TensorFlow Lite as the trusted, high-performance runtime for on-device AI. Now with LiteRT Next, we're expanding our vision with a new generation of APIs designed for…

一款基于 AI 技术的 Web 应用程序，可将文本内容智能转换为 Mermaid 格式的代码，并将其渲染成可视化图表。

kernels, of the mega variety

Conan - The open-source C and C++ package manager

”数学不难“ 之 《线性代数不难》上下册，66话题完册；欢迎批评指正

Hurl, run and test HTTP requests with plain text.