Starred repositories
Papers from the computer science community to read and discuss.
the easiest way to run natural language-described workflows automatically
init to record my learning path of AI Infra, especially on inference.
Modern photo gallery for photographers, with S3/GitHub sync, EXIF details, maps, and a WebGL viewer.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
本项目是一个面向小白开发者的大模型应用开发教程，在线阅读地址：https://datawhalechina.github.io/llm-universe/
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。
The reliability of disk images, the flexibility of files
cert-manager webhook resolver for DNSPod
Source code for Practical DB-OS Co-Design with Privileged Kernel Bypass
Run docker like persistent rootfs container in kubernetes
One second to read GitHub code with VS Code.
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
Learning English through the method of constructing sentences with conjunctions
An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.
🪄 Create rich visualizations with AI
Janus-Series: Unified Multimodal Understanding and Generation Models
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 20+ clouds, or on-prem).
PDF++: the most Obsidian-native PDF annotation & viewing tool ever. Comes with optional Vim keybindings.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Capturing SSL/TLS plaintext without a CA certificate using eBPF. Supported on Linux/Android kernels for amd64/arm64.
