AI Agent Skills

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python,…

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Linux运维监控工具，支持系统硬件信息，内存，CPU，温度，磁盘空间及IO，硬盘smart，GPU，防火墙，网络流量速率等监控，服务接口监测，大屏展示，拓扑图，端口监控，进程监控，docker监控，日志监控，文件防篡改，数据库监控，指令批量下发执行，web ssh，Linux面板(探针)，告警，SNMP监测，K8S，Redis，Ngi…

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/multiplatform CPU, AMD, NVIDIA GPU PyTorch support, handling, and auto-stitching

The fastest way to turn a Jupyter notebook into a beautiful, shareable web app — no callbacks, no frontend, no rewrite.

Modular ZK(Zero Knowledge) backend accelerated by GPU

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further e…

Run Keras models in the browser, with GPU support using WebGL

The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

GPU-accelerated force graph layout and rendering

Detect local hardware (RAM, CPU, GPU/VRAM) and recommend the best-fit local LLM models with optimal quantization, speed estimates, and fit scoring.

Generate a standup update from recent activity. Use when preparing for daily standup, summarizing yesterday's commits and PRs and ticket moves, formatting work into yest…

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when use…