Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Testtimescaling Testtimescaling github io GitHub Pages Course Progression
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Openai Openai node Structured Output Parsing
- Workflow:Haosulab ManiSkill Imitation Learning Pipeline
- Workflow:Bigscience workshop Petals Prompt Tuning Chatbot
- Workflow:Obss Sahi COCO Dataset Slicing
- Workflow:Onnx Onnx Model Validation
- Workflow:Allenai Open instruct Tulu3 Full Post Training
- Workflow:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Mage ai Mage ai API Source Extraction
Principles
- Principle:Duckdb Duckdb Enum Code Generation
- Principle:Eventual Inc Daft Arrow Export
- Principle:Farama Foundation Gymnasium Environment Error Handling
- Principle:Diagram of thought Diagram of thought Task Requirements Definition
- Principle:Ollama Ollama GGUF Model Conversion Phi3
- Principle:Tensorflow Serving JSON Response Serialization
- Principle:Run llama Llama index Finetuned Model Retrieval
- Principle:Pytorch Serve API Integration Testing
- Principle:Cohere ai Cohere python Rerank Response Processing
- Principle:Protectai Llm guard Output Relevance Checking
Implementations
- Implementation:ARISE Initiative Robosuite DomainRandomizationWrapper
- Implementation:Duckdb Duckdb Add Library Unity
- Implementation:ClickHouse ClickHouse BorrowedObjectPool
- Implementation:Open compass VLMEvalKit TDBench Utils
- Implementation:Openai Openai python Vector Store Create Params
- Implementation:Pola rs Polars SQLContext Register
- Implementation:Huggingface Transformers Add Adapter For QLoRA
- Implementation:Haosulab ManiSkill RoboCasaSceneBuilder
- Implementation:Openai Openai python Shared Compound Filter
- Implementation:NVIDIA NeMo Curator TransNetV2ClipExtractionStage
Heuristics
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:Marker Inc Korea AutoRAG OpenAI Rate Limit Mitigation
- Heuristic:SeldonIO Seldon core Over Commit Memory Tip
- Heuristic:ClickHouse ClickHouse Debug Build Tips
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:Sktime Pytorch forecasting Batch Size Selection
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
- Heuristic:NVIDIA DALI NVJPEG Memory Preallocation
- Heuristic:NVIDIA DALI Thread Affinity Optimization
Environments
- Environment:Sgl project Sglang ROCm
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Intel Ipex llm Build Environment
- Environment:Langchain ai Langchain Unit Test Network Isolation
- Environment:Apache Beam Portable Runner Environment
- Environment:Open compass VLMEvalKit Python Runtime Environment
- Environment:Sgl project Sglang CUDA SM100
- Environment:Pytorch Serve Distributed Training Environment
- Environment:Isaac sim IsaacGymEnvs Python CUDA Runtime