Main Page
Welcome to Leeroopedia
Your ML & Data Knowledge Wiki. Best practices and expert-level knowledge for Machine Learning and Data Engineering, covering 1000+ frameworks and libraries from training to deployment.
Browse implementation patterns, configuration guides, debugging heuristics, and battle-tested defaults for frameworks like vLLM, DeepSpeed, Megatron-LM, FlashAttention, Triton, Unsloth, LangChain, and many more. Every page is structured so both humans and AI agents can find what they need fast.
Connect your AI coding agent. Plug Leeroopedia into your favorite coding agent, and let it build robust AI/ML systems autonomously:
- SuperML plugin — converts your AI coding agent into an expert ML engineer with agentic memory
- Leeroopedia MCP — search over best-practices and skills of ML/AI
- Kapso — experimentation platform for autonomous AI/ML software building
Browse by Category
| Category | Description | Browse |
|---|---|---|
| Workflows | Step-by-step processes and procedures | Browse All |
| Principles | Core ideas and foundational knowledge | Browse All |
| Implementations | Code-level details and modules | Browse All |
| Heuristics | Best practices and guidelines | Browse All |
| Environments | Setup and configuration guides | Browse All |
Explore Pages
Workflows
- Workflow:PeterL1n BackgroundMattingV2 Video matting inference
- Workflow:Mlc ai Web llm Chrome Extension Integration
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:ContextualAI HALOs Online Iterative Alignment
- Workflow:Princeton nlp SimPO Model Inference
- Workflow:HKUDS AI Trader Data Pipeline
- Workflow:InternLM Lmdeploy VLM Inference Pipeline
- Workflow:Openai Openai agents python Streaming Agent Execution
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:OpenHands OpenHands Organization Onboarding
Principles
- Principle:Langgenius Dify Model Provider Management
- Principle:Tencent Ncnn Top K Classification
- Principle:Kserve Kserve InferenceService Specification
- Principle:Ggml org Llama cpp ResourceManagement
- Principle:Google deepmind Mujoco GLFW Window Management
- Principle:Neuml Txtai Text Tokenization
- Principle:AUTOMATIC1111 Stable diffusion webui Merge output options
- Principle:Ollama Ollama GGUF Model Conversion GlmOcr
- Principle:NVIDIA TransformerEngine Fused LayerNorm MLP
- Principle:Apache Druid Supervisor Operational Management
Implementations
- Implementation:Duckdb Duckdb Regression Test Scripts
- Implementation:Openai Openai node Cloudflare Worker Lockfile
- Implementation:InternLM Lmdeploy XgrammarBind
- Implementation:Tensorflow Serving Hashmap Source Adapter
- Implementation:InternLM Lmdeploy AttentionMainloopSm80
- Implementation:Haosulab ManiSkill GroundBuilder
- Implementation:Google deepmind Mujoco MJWarp Sensor
- Implementation:Ggml org Llama cpp Unicode Data
- Implementation:Tensorflow Serving Aspired Versions Manager Benchmark
- Implementation:Datajuicer Data juicer S3DownloadFileMapper
Heuristics
- Heuristic:Intel Ipex llm NF4 Quantization Best Practice
- Heuristic:Kubeflow Kubeflow Stale Issue Lifecycle Management
- Heuristic:LaurentMazare Tch rs Safetensors Format Preference
- Heuristic:Datahub project Datahub Validation Cross API
- Heuristic:Microsoft BIPIA OpenAI Rate Limit Retry
- Heuristic:Microsoft Agent framework Function Invocation Defaults
- Heuristic:Dotnet Machinelearning AutoML SMAC Dimension Limit
- Heuristic:Explodinggradients Ragas Embedding Batch Size Tuning
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
Environments
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Nautechsystems Nautilus trader Binance API Credentials
- Environment:Mlc ai Mlc llm WebGPU Browser Environment
- Environment:Scikit learn Scikit learn OpenMP Thread Configuration
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Microsoft Autogen LLM Provider API Keys
- Environment:Huggingface Optimum Python Core Dependencies
- Environment:Astronomer Astronomer cosmos Python Airflow Runtime
- Environment:Facebookresearch Habitat lab SLURM Distributed Environment
- Environment:Googleapis Python genai Gemini API Key Authentication