Lists (22)
00. ⌨️ Dev Environments ⌨️
Technologies, tools, and configurations I use for my development environment.104 repositories
01. 🦙 Model: LLM 🦙
Repositories for Large Language Models (LLM), frameworks, and datasets.20 repositories
01. 💾 Stack: Backend 💾
Frameworks, libraries, and technologies for building and maintaining backend systems.49 repositories
01. 📡 Stack: DevOps 📡
Tools, platforms, and practices for DevOps, including CI/CD, automation, and infrastructure.63 repositories
01. 🛰️ Stack: MLOps 🛰️
A comprehensive list of tools and platforms for Machine Learning Operations (MLOps).118 repositories
01. 🐍 Stack: Python 🐍
Useful Python modules and libraries that I frequently use.115 repositories
01. 🚄 Stack: XPU 🚄
Libraries, tools, and frameworks for XPU (GPU, TPU, NPU, ...) programming, focusing on CUDA and kernel optimization.45 repositories
02. 🤖 Model: ML 🤖
Repositories for Machine Learning (ML) models, frameworks, and datasets.48 repositories
02. 🧑🏻🔧 Stack: Agent 🧑🏻🔧
Repositories related to AI Agents, including LLM-based autonomous agents and multi-agent systems.70 repositories
03. 🐥 Stack: Frontend 🐥
Frameworks, libraries, and tools for frontend development.22 repositories
98: 🧑🏭 Study: Agent 🧑🏭
A study list of repositories for learning about and experimenting with AI Agents.8 repositories
98. 💿 Study: Backend 💿
Educational resources and projects for learning backend development.27 repositories
98. 🔬 Study: DevOps 🔬
A study guide to DevOps, containing tutorials, guides, and example projects.18 repositories
98. 👶🏻 Study: Frontend 👶🏻
Learning resources for frontend technologies, frameworks, and design patterns.6 repositories
98. 🦾 Study: ML 🦾
Educational materials, tutorials, and projects for studying Machine Learning (ML).20 repositories
98. 🚀 Study: MLOps 🚀
A curated study list for understanding and implementing MLOps pipelines and practices.48 repositories
98. 🚅 Study: XPU 🚅
Resources dedicated to learning XPU (GPU, TPU, NPU, ...) programming, focusing on CUDA and GPU Kernels.18 repositories
99. 🐘 BOAZ 🐘
Projects and materials from my activities at BOAZ, Korea's first inter-university big data club.11 repositories
99. 🔭 Career 🔭
Resources for career development, interview preparation, and job searching.42 repositories
99. 🧗 Conferences 🧗
My speaking engagements, presentations, and materials from conferences.2 repositories
99. 💻 Etc. 💻
Miscellaneous repositories, tools, and interesting projects that don't fit into other categories.47 repositories
99. 📑 GitHub Pages 📑
Tools, themes, and examples for building static sites with GitHub Pages.22 repositories
Starred repositories
Official inference repo for FLUX.2 models
Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.
Curated collection of AI inference engineering resources — LLM serving, GPU kernels, quantization, distributed inference, and production deployment. Compiled from the AER Labs community.
Kernel sources for https://huggingface.co/kernels-community
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Dynamic Memory Management for Serving LLMs without PagedAttention
NVIDIA vGPU Device Manager manages NVIDIA vGPU devices on top of Kubernetes
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.
Cloud-Native distributed storage built on and for Kubernetes
Ceph is a distributed object, block, and file storage platform
Free and Open Source, Distributed, RESTful Search Engine
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Community maintained hardware plugin for vLLM on AWS Neuron
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
Source code formatter for cmake listfiles.
NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs
HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container