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:HKUDS AI Trader Multi Agent Comparison
- Workflow:Groq Groq python Text To Speech
- Workflow:Truera Trulens Custom App Instrumentation And Evaluation
- Workflow:Kubeflow Kubeflow Contributing To Kubeflow
- Workflow:NVIDIA NeMo Aligner REINFORCE Training
- Workflow:Datahub project Datahub Java SDK V2 Entity Management
- Workflow:Mlc ai Web llm Text Embeddings And RAG
- Workflow:Huggingface Datasets Dataset Loading and Exploration
- Workflow:Openai Openai agents python Tool Integrated Agent
- Workflow:Tencent Ncnn Image Classification Inference
Principles
- Principle:Explodinggradients Ragas Testset Export
- Principle:Danijar Dreamerv3 Distributed Actor Inference
- Principle:Online ml River Estimator Validation Framework
- Principle:Run llama Llama index Text Chunking
- Principle:Pytorch Serve Inference Handler Development
- Principle:NVIDIA TransformerEngine Activation Checkpointing
- Principle:Huggingface Datatrove IPC Data Reading
- Principle:Haotian liu LLaVA Batch VQA Inference
- Principle:Langgenius Dify Documentation
- Principle:Togethercomputer Together python LLM Evaluation
Implementations
- Implementation:Diagram of thought Diagram of thought Iterative Reasoner Prompt Loading
- Implementation:TobikoData Sqlmesh PlanBuilder Forward Only
- Implementation:Microsoft DeepSpeedExamples GptFinetuning AnalyzeData
- Implementation:Zai org CogVideo Get Video Frames
- Implementation:Apache Paimon RESTCatalogOptions
- Implementation:Googleapis Python genai Tunings Get
- Implementation:Microsoft Onnxruntime CPU GRU IOUtils
- Implementation:Openclaw Openclaw ResolveEffectiveToolPolicy
- Implementation:Treeverse LakeFS Java SDK Model SetupState
- Implementation:Arize ai Phoenix Prompts Create Version
Heuristics
- Heuristic:MaterializeInc Materialize CI Retry Strategies
- Heuristic:Openai CLIP JIT Vs Non JIT Loading
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:Openclaw Openclaw Plugin Dependency Gotchas
- Heuristic:Marker Inc Korea AutoRAG Module Selection Strategies
- Heuristic:Eric mitchell Direct preference optimization TF32 Matmul Precision
- Heuristic:Google deepmind Dm control Prop Settling Physics Tuning
- Heuristic:LMCache LMCache Health Monitor Thresholds
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:Predibase Lorax CUDA Graph Batch Size Caching
Environments
- Environment:Helicone Helicone Python ClickHouse Migrations
- Environment:Helicone Helicone Wrangler CLI
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:Huggingface Transformers BitsAndBytes Quantization Env
- Environment:Huggingface Optimum GPTQ Quantization Environment
- Environment:DataExpert io Data engineer handbook PostgreSQL Docker Environment
- Environment:Intel Ipex llm NPU Cpp Environment
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment