Productive, portable, and performant GPU programming in Python.
- taichi
- differentiable-programming
- gpu-programming
- sparse-computation
132,241 visible repositories in the index
1–24 of 24 · Most stars
Productive, portable, and performant GPU programming in Python.
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
A General-purpose Task-parallel Programming System in C++
Translated:anchor: A collection of reading notes from my career as a game programmer. You can think of it as an enhanced blog. It covers graphics, real-time rendering, programming practice, GPU programming, design patterns, software engineering, and more. Keep Reading , Keep Writing , Keep Coding.
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
A modular and open-ended toolkit for WebGPU, with advanced type inference and the ability to write shaders in TypeScript
A GPU-powered real-time analytics storage and query engine.
TranslatedCovers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning
CUDA Core Compute Libraries
Sample codes for my CUDA programming book
The write-once-run-anywhere GPGPU library for Rust
Computations and statistics on manifolds with geometric structures.
A tutorial on modern GPU programming for machine learning systems
:cd: CD Content ( Source Code ) Collection of Book <GPU Gems > 1~ 3 | 《GPU精粹》 1~ 3 随书CD(源代码)珍藏
A curated list of best cuda programming books
An Axum-based Rust web framework with Lean 4-verifiable application kernels that run on servers, bare-metal embedded devices, and GPUs, plus integrated security testing.
Examples demonstrating available options to program multiple GPUs in a single node or a cluster
Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。
Robust real-time rendering engine on DX11, DX12 with many advanced graphical features for quick prototyping
:cd: Source Code Collection of Book <GPU Pro> 1~ 7 | 《GPU Pro》1~ 7 书本源代码珍藏
Vulkan compute for people
A high-performance engine for matrix math, physics simulation, and MCAD and ECAD as code. RunMat checks types, sizes and units before anything runs, executes on CPU and GPU, and runs existing MATLAB-language code as written.