分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
☆2,046Apr 30, 2026Updated this week
Alternatives and similar repositories for InfraTech
Users that are interested in InfraTech are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A tutorial for CUDA&PyTorch☆420Mar 23, 2026Updated last month
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆10,825Apr 20, 2026Updated 2 weeks ago
- Examples of CUDA implementations by Cutlass CuTe☆272Jul 1, 2025Updated 10 months ago
- My learning notes for ML SYS.☆6,166Apr 23, 2026Updated last week
- 《自己动手写AI编译器》☆38Oct 19, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Nano vLLM☆13,219Apr 26, 2026Updated last week
- how to optimize some algorithm in cuda.☆2,960Updated this week
- Material for gpu-mode lectures☆6,040Apr 22, 2026Updated last week
- High Performance LLM Inference Operator Library☆838Apr 13, 2026Updated 3 weeks ago
- AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术☆16,708Sep 3, 2025Updated 8 months ago
- NVIDIA cuTile learn☆168Dec 9, 2025Updated 4 months ago
- 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。☆6,905Dec 22, 2025Updated 4 months ago
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,198Apr 20, 2026Updated 2 weeks ago
- Nano vLLM with vLLM v1's request scheduling strategy and chunked prefill☆81Jan 26, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CUDA 算子手撕与面试指南☆956Aug 23, 2025Updated 8 months ago
- 注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能☆183Aug 11, 2025Updated 8 months ago
- Learning TileLang with 10 puzzles!☆235Apr 28, 2026Updated last week
- 《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）☆4,802Mar 15, 2026Updated last month
- FlashInfer: Kernel Library for LLM Serving☆5,544Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,094Mar 13, 2026Updated last month
- ☆65Feb 5, 2026Updated 3 months ago
- Implement a Pytorch-like DL library in C++ from scratch, step by step☆270Apr 15, 2026Updated 3 weeks ago
- 这一生听过许多道理，但还是过不好这一生，这是因为缺少真正的动手实践，光听道理，缺少动手实践的过程，学习难免会让人觉得味同嚼蜡，所以我的分享都比较倾向于实践，在一次次动手实践的过程中感受知识原本纯真的模样。☆14Jun 28, 2023Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated 8 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,242Updated this week
- High performance inference engine for diffusion models☆107Sep 5, 2025Updated 8 months ago
- ☆31May 28, 2024Updated last year
- ☆14Nov 3, 2025Updated 6 months ago
- This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.☆426Mar 1, 2026Updated 2 months ago
- Machine Learning Engineering Open Book☆17,854Mar 16, 2026Updated last month
- learning how CUDA works☆386Mar 3, 2025Updated last year
- a computing kernel implementation in ML inference framework aiming at theoretical limit☆12Dec 18, 2019Updated 6 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆26,832Updated this week
- compiler learning resources collect.☆2,722Mar 19, 2025Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,036Updated this week
- This project aims to replicate mainstream open-source model architectures with limited computational resources, implementing mini models …☆180Apr 27, 2026Updated last week
- hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等☆440Apr 27, 2026Updated last week
- ☆123Sep 22, 2025Updated 7 months ago
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆18Jul 10, 2025Updated 9 months ago