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:Microsoft Playwright Browser automation CLI
- Workflow:PacktPublishing LLM Engineers Handbook Digital Data ETL
- Workflow:LaurentMazare Tch rs Pretrained Image Classification
- Workflow:Openai Openai python Image Generation
- Workflow:PrefectHQ Prefect Per Worker Task Concurrency
- Workflow:Obss Sahi COCO Evaluation
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:Neuml Txtai Agent Orchestration
- Workflow:Langgenius Dify Application Creation
- Workflow:Princeton nlp SimPO Model Inference
Principles
- Principle:PrefectHQ Prefect Dependency Lockfile Management
- Principle:NVIDIA TransformerEngine Activation Checkpointing
- Principle:Triton inference server Server Ensemble Configuration
- Principle:DistrictDataLabs Yellowbrick Cross Validation Scoring
- Principle:Online ml River Multi Output Metrics
- Principle:Treeverse LakeFS Imported Data Verification
- Principle:OpenBMB UltraFeedback Instruction Sampling
- Principle:Cypress io Cypress CI Result Processing
- Principle:Evidentlyai Evidently Dataset Creation
- Principle:Ollama Ollama Anthropic API Compatibility
Implementations
- Implementation:CrewAIInc CrewAI Flow Routing Primitives
- Implementation:Scikit learn Scikit learn FetchCaliforniaHousing
- Implementation:Elevenlabs Elevenlabs python AgentBranchSummary
- Implementation:Predibase Lorax Response Format Type
- Implementation:Avhz RustQuant FractionalBrownianMotion
- Implementation:Treeverse LakeFS SetGCRules
- Implementation:NVIDIA DALI Fn Resize Linear
- Implementation:ARISE Initiative Robomimic ConfigGenerator
- Implementation:Tensorflow Serving Threadpool Executor
- Implementation:NVIDIA DALI PyTorch Output Integration
Heuristics
- Heuristic:NVIDIA NeMo Aligner Higher Stability Log Probs
- Heuristic:Openai Evals Eval Resumption Strategy
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Before Split Leakage
- Heuristic:OpenHands OpenHands Streamable HTTP Over SSE
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Alibaba MNN Weight Quantization Strategy
- Heuristic:ARISE Initiative Robomimic Checkpoint Selection Strategy
- Heuristic:SqueezeAILab ETS Softmax Temperature Tuning
- Heuristic:Trailofbits Fickling Severity Threshold Selection
- Heuristic:PacktPublishing LLM Engineers Handbook RAG Retrieval Parameters
Environments
- Environment:Vllm project Vllm Python Dependencies
- Environment:LaurentMazare Tch rs Python Interop Environment
- Environment:OpenHands OpenHands Integration Credentials
- Environment:Openclaw Openclaw Node 22 Runtime
- Environment:Intel Ipex llm Pipeline Parallel Environment
- Environment:Apache Druid Integration Test Docker
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:CarperAI Trlx DeepSpeed Multi GPU
- Environment:Apache Hudi Docker Demo Environment
- Environment:Junyanz Pytorch CycleGAN and pix2pix Python PyTorch Runtime