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:NVIDIA NeMo Aligner REINFORCE Training
- Workflow:Openai Openai agents python Basic Agent Execution
- Workflow:Helicone Helicone Integrate Provider To Gateway
- Workflow:Openclaw Openclaw Channel Connection
- Workflow:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:ContextualAI HALOs Reward Model Training
- Workflow:Guardrails ai Guardrails Custom Validator Development
- Workflow:DevExpress Testcafe CI Integration
- Workflow:Spotify Luigi Database Ingestion Pipeline
Principles
- Principle:Wandb Weave Auto Patching
- Principle:Unslothai Unsloth AIME Evaluation
- Principle:Huggingface Datasets Environment Reporting
- Principle:ARISE Initiative Robosuite MJCF Model Hierarchy
- Principle:Anthropics Anthropic sdk python Token Counting And Batching
- Principle:Nightwatchjs Nightwatch Cucumber Test Execution
- Principle:Duckdb Duckdb Source Package Building
- Principle:Snorkel team Snorkel Multitask Training Execution
- Principle:Ggml org Llama cpp Evaluation Parameter Configuration
- Principle:Duckdb Duckdb Release Artifact Upload
Implementations
- Implementation:Apache Flink CompactCoordinator ProcessElement
- Implementation:Rapidsai Cuml Decomposition Params
- Implementation:NVIDIA NeMo Curator RayClient
- Implementation:CARLA simulator Carla CMake Build Launch Package
- Implementation:FlagOpen FlagEmbedding Reinforced IR Model
- Implementation:Apache Paimon IntervalPartition
- Implementation:Run llama Llama index BaseExtractor
- Implementation:Unslothai Unsloth GEMM Forward Kernel
- Implementation:MaterializeInc Materialize Repository Init
- Implementation:Zai org CogVideo FSQ
Heuristics
- Heuristic:Onnx Onnx Opset Version Selection
- Heuristic:SeldonIO Seldon core Tracing Latency Tip
- Heuristic:Openai Openai agents python MCP Server Lifecycle Management
- Heuristic:Datajuicer Data juicer Operator Fusion Rules
- Heuristic:Microsoft Agent framework Tool Approval Mode Production
- Heuristic:Haotian liu LLaVA Quantization MM Projector Exclusion
- Heuristic:Norrrrrrr lyn WAInjectBench Balanced Class Weights Imbalanced Data
- Heuristic:Facebookresearch Habitat lab Mini Batch Environment Divisibility
- Heuristic:Pola rs Polars Streaming For Large Datasets
- Heuristic:Vibrantlabsai Ragas Concurrency And Retry Configuration
Environments
- Environment:Google deepmind Mujoco Python Bindings Environment
- Environment:NVIDIA DALI TensorFlow Environment
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:ArroyoSystems Arroyo Object Storage
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Huggingface Trl Python Core Dependencies
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Vespa engine Vespa Docker OCI Container Runtime
- Environment:Openai Evals OpenAI API Configuration