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:Huggingface Open r1 SFT Distillation
- Workflow:Huggingface Diffusers Checkpoint Conversion
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:MaterializeInc Materialize Upgrade Testing
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:Eventual Inc Daft Data Lakehouse ETL
- Workflow:Huggingface Trl Reward Model Training
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Danijar Dreamerv3 Single Process Training
Principles
- Principle:Iamhankai Forest of Thought LLM Pipeline Loading
- Principle:Neuml Txtai API Server Bootstrap
- Principle:Google research Deduplicate text datasets Dataset Serialization TFDS
- Principle:Dagster io Dagster Data Quality Validation
- Principle:Langgenius Dify Service Layer Architecture
- Principle:Microsoft Agent framework Conditional Routing
- Principle:ArroyoSystems Arroyo Pipeline Submission
- Principle:LMCache LMCache Prefill Decode Configuration
- Principle:NVIDIA DALI PyTorch Iterator
- Principle:Explodinggradients Ragas Genetic Prompt Optimization
Implementations
- Implementation:Kornia Kornia Hyperplane
- Implementation:Online ml River Base DriftDetector
- Implementation:Mlc ai Mlc llm Serve
- Implementation:Datahub project Datahub SparkPathUtils
- Implementation:Eventual Inc Daft Read Csv
- Implementation:Haosulab ManiSkill ActionRepeatWrapper
- Implementation:Avhz RustQuant Surface
- Implementation:Langfuse Langfuse BlobStorageLog Repository
- Implementation:Datajuicer Data juicer Compress Utils
- Implementation:Langchain ai Langgraph EncryptedSerializer
Heuristics
- Heuristic:Diagram of thought Diagram of thought Acyclicity Constraint Enforcement
- Heuristic:Norrrrrrr lyn WAInjectBench LoRA Rank Alpha Selection
- Heuristic:Vespa engine Vespa Document Batch Processing Strategy
- Heuristic:Mage ai Mage ai Record Deduplication Before Batch Export
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
- Heuristic:Microsoft Semantic kernel Prompt Injection Safety
- Heuristic:Huggingface Alignment handbook QLoRA Learning Rate Scaling
- Heuristic:OpenHands OpenHands Clustered Race Condition Prevention
- Heuristic:Sktime Pytorch forecasting Early Stopping Patience
- Heuristic:Fastai Fastbook Random Forest Defaults
Environments
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Shiyu coder Kronos Comet ML Logging
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Intel Ipex llm Build Environment
- Environment:PacktPublishing LLM Engineers Handbook Selenium Chrome Crawler Environment
- Environment:Tensorflow Serving Python Client Environment
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Haosulab ManiSkill GPU CUDA Simulation
- Environment:Apache Beam Portable Runner Environment
- Environment:Intel Ipex llm XPU Finetuning Environment