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:Snorkel team Snorkel Slice Aware Training
- Workflow:Truera Trulens RAG With Guardrails
- Workflow:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:NVIDIA NeMo Aligner Reward Model Training
- Workflow:Datajuicer Data juicer Text Data Processing Pipeline
- Workflow:ARISE Initiative Robomimic Dataset Preparation Pipeline
- Workflow:Apache Dolphinscheduler Workflow Failover Recovery
- Workflow:Run llama Llama index RAG Query Pipeline
- Workflow:Openai Openai agents python Guardrails Secured Agent
- Workflow:Huggingface Diffusers Text to Image Inference
Principles
- Principle:Openai Openai python Response Processing
- Principle:Neuml Txtai Document Preparation
- Principle:FlowiseAI Flowise Vector Store Upsert
- Principle:Guardrails ai Guardrails CLI Configuration
- Principle:Langchain ai Langchain Embedding Model Initialization
- Principle:Huggingface Datasets Dataset Builder Resolution
- Principle:Nautechsystems Nautilus trader Instrument Registration
- Principle:Haosulab ManiSkill Physics Struct Abstraction
- Principle:InternLM Lmdeploy Chat Template Formatting
- Principle:Dagster io Dagster Sensor Driven Pipelines
Implementations
- Implementation:DistrictDataLabs Yellowbrick InterclusterDistance Visualizer
- Implementation:InternLM Lmdeploy Pipeline Chat VLM
- Implementation:Langchain ai Langchain VectorStore Add Documents
- Implementation:Pyro ppl Pyro PlateMessenger
- Implementation:OWASP Www project top 10 for large language model applications GitHubActionChecker Check File
- Implementation:Ggml org Llama cpp Chat Parser Xml Toolcall
- Implementation:Lance format Lance Encoding Block Statistics
- Implementation:Open compass VLMEvalKit HunyuanWrapper
- Implementation:Infiniflow Ragflow TagFeatureItem Component
- Implementation:ClickHouse ClickHouse Poco NetworkInterface Impl
Heuristics
- Heuristic:Ggml org Ggml Quantization Type Selection
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:NVIDIA DALI Thread Affinity Optimization
- Heuristic:Langgenius Dify Env Sync Upgrade Strategy
- Heuristic:SqueezeAILab ETS Embedding Model GPU Collocation
- Heuristic:Nightwatchjs Nightwatch Timeout And Retry Tuning
- Heuristic:Iterative Dvc Shell Execution Pitfalls
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:Run llama Llama index Batch Eval Retry Strategy
- Heuristic:DevExpress Testcafe Concurrency Factor Limit
Environments
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:Datahub project Datahub Java 17 Backend Environment
- Environment:Eventual Inc Daft AI Provider Dependencies
- Environment:Microsoft Onnxruntime CPU Training Environment
- Environment:Sgl project Sglang Multi Platform Accelerators
- Environment:Huggingface Datasets PyTorch Integration
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Kubeflow Pipelines KFP Backend Deployment
- Environment:Axolotl ai cloud Axolotl Python Runtime