Starred repositories
Agent Skills for Google products and technologies
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Source code repo for book: Hands-On LLM Serving and Optimization: Hosting LLMs at Scale
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
Integrating Mamba/SSMs with Transformer for Enhanced Long Context and High-Quality Sequence Modeling
Tổng hợp các khóa học miễn phí và hữu ích từ **NVIDIA Deep Learning Institute (DLI)**. Phù hợp cho AI/ML Engineer, Data Scientist, và Developer muốn học về **Data Science, CUDA, Generative AI, RAG,…
1
Updated Sep 16, 2025
High-performance CUDA implementation of Muon optimizer for LLM training. Features Newton-Schulz polar decomposition, cuBLAS acceleration, and transpose optimization for 8x FLOP savings on transform…
CUDA kernels for the Muon optimizer: Newton-Schulz polar iteration (quintic + Gram-NS variants), benchmarked and verified against torch.optim.Muon.
Reproduction of Thinking Machines' modular-manifolds CIFAR experiment, with CUDA/MPS/CPU support
SIGMA -> SIGMA Integrates GPUs into Muon Analysis | a Muon segment formation cuda algorithm
GPU integration using CUDA of a phase space integral.
Newton-Muon + Preconditioned Optimizers for MoE Training at scale, with out-of-the-box support for MuP and FSDP support for Muon, built on top of Megatron-LM and TransformerEngine.
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
基于Spring Boot的在线考试系统(预览地址 http://129.211.88.191 ，账户分别是admin、teacher、student，密码是admin123)，也有Python实现
Smart contracts for the staking modules of the Lido protocol
Survey on Multimodal Embodied Agents: From Computer-Use to Robot-Use
A spy satellite simulator in your browser, except the data is real. Live open source spatial intelligence on a photorealistic 3D globe.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
具身智能学习手册 - 覆盖VLA模型、遥操作、Sim2Real、强化学习等完整知识体系的系统性学习指南
Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view …
宽宝 QuantBuddy： 一整套面向Agent Invesment投资研究与决策的底层设施与能力的调用skill， 覆盖A股/港股/美股/期货/宏观/ETF的量化分析与计算。支持行情、估值、财务查询、选股筛选、因子计算、策略回测。A complete infrastructure for Agent based investment analysis and decision throu…
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
Achieve state of the art inference performance with modern accelerators on Kubernetes
Notes of the book System Desgin Interview - An Insider's Guide