分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
☆3,896Aug 7, 2026Updated last month
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☆515Mar 23, 2026Updated 5 months ago
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,939Updated this week
- Nano vLLM☆15,411Apr 26, 2026Updated 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。☆8,175Dec 22, 2025Updated 8 months ago
- My learning notes for ML SYS.☆7,331Updated this week
- 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.
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,032May 17, 2026Updated 3 months ago
- AI Infra 全栈从0入门学习资料：https://caomaolufei.github.io/AIInfraGuide/☆2,091Updated this week
- hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等☆708Apr 27, 2026Updated 4 months ago
- High Performance LLM Inference Operator Library☆1,157Updated this week
- ☆814Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,384Updated this week
- This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.☆585Mar 1, 2026Updated 6 months ago
- 🍎 One kernel a day keeps high latency away. A hands-on CUDA learning path featuring a rich collection of kernels, from the basics to pea…☆214Aug 29, 2026Updated 2 weeks ago
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆1,028Aug 29, 2026Updated 2 weeks 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☆1,108Aug 23, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,562Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,395Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆35,850Updated this week
- how to optimize some algorithm in cuda.☆3,261Updated this week
- slime is an LLM post-training framework for RL Scaling.☆8,447Sep 3, 2026Updated last week
- A tutorial on modern GPU programming for machine learning systems☆1,267Sep 3, 2026Updated last week
- A self-learning tutorail for CUDA High Performance Programing.☆1,107Jan 14, 2026Updated 7 months ago
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆992Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A high-throughput and memory-efficient inference and serving engine for LLMs☆91,571Updated this week
- AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。☆2,634Updated this week
- 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☆17,790Sep 3, 2025Updated last year
- 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☆209Aug 11, 2025Updated last year
- 本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）☆25,040Jul 19, 2026Updated last month
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,496Aug 14, 2026Updated 3 weeks ago
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,165Updated this week
- This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference sp…☆75Apr 24, 2026Updated 4 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,396Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Implement a Pytorch-like DL library in C++ from scratch, step by step☆375Apr 15, 2026Updated 4 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,759Aug 13, 2026Updated 3 weeks ago
- An LLM post-training framework with vLLM for RL Scaling☆458Updated this week
- Material for gpu-mode lectures☆6,581Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,818Updated this week
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆4,560Updated this week
- High-performance RL post-training infrastructure. Designed to achieve bitwise operator-level train-inference consistency across heterogen…☆296Updated this week