Lists (1)
Starred repositories
Fast and memory-efficient exact attention
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel
FlashInfer: Kernel Library for LLM Serving
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
Natural language detection library for Rust. Try demo online: https://whatlang.org/
Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.
A cross-platform, safe, pure-Rust graphics API.
《Build a Large Language Model (From Scratch)》是一本深入探讨大语言模型原理与实现的电子书，适合希望深入了解 GPT 等大模型架构、训练过程及应用开发的学习者。为了让更多中文读者能够接触到这本极具价值的教材，我决定将其翻译成中文，并通过 GitHub 进行开源共享。
aha model inference library, now supports Qwen2.5VL, MiniCPM4, VoxCPM, Qwen3VL, DeepSeek-OCR, and Hunyuan-OCR, VoxCPM1.5, RMBG2.0, GLM-ASR-Nano-2512
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/
General purpose 3D and 2D game engine using Go (golang) and Vulkan with built in editor
Userspace eBPF runtime for Observability, Network, GPU & General Extensions Framework
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。
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
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
EasyDB is a lightweight desktop app built with Tauri and Rust, enabling you to query local CSV, Excel, and JSON files with SQL—no external database required. It handles datasets from hundreds of MB…
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
Linux virtual machines, with a focus on running containers
vsag is a vector indexing library used for similarity search.
An Awesome List for getting started with web archiving
HTML parsing and querying with CSS selectors
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
