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:OpenRLHF OpenRLHF Iterative DPO
- Workflow:Webdriverio Webdriverio Cloud Service Integration
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:ClickHouse ClickHouse Packaging For Distribution
- Workflow:PrefectHQ Prefect Dbt Model Orchestration
- Workflow:Googleapis Python genai Multimodal Content Generation
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:PrefectHQ Prefect Web Scraping Pipeline
- Workflow:NVIDIA NeMo Curator Semantic Deduplication
- Workflow:Alibaba MNN Model Conversion Pipeline
Principles
- Principle:Online ml River Drift Adaptive Evaluation
- Principle:Iamhankai Forest of Thought CGDM Answer Selection
- Principle:Togethercomputer Together python Batch Result Retrieval
- Principle:SqueezeAILab ETS ILP Node Selection
- Principle:Duckdb Duckdb Regression Analysis And Reporting
- Principle:Microsoft Semantic kernel Metadata Filtering
- Principle:Openclaw Openclaw Container Storage Configuration
- Principle:Langgenius Dify Vector Database Selection
- Principle:Tensorflow Serving Executor Abstraction
- Principle:TA Lib Ta lib python Abstract Function Execution
Implementations
- Implementation:NVIDIA TransformerEngine Swizzle C API
- Implementation:Huggingface Datasets Dataset With Format
- Implementation:Open compass VLMEvalKit MedqbenchPairedDescriptionDataset
- Implementation:Risingwavelabs Risingwave OpensearchRestHighLevelClientAdapter
- Implementation:Microsoft Playwright FfPage
- Implementation:Ollama Ollama Llama Model Granite Hybrid
- Implementation:Sail sg LongSpec Tree Spec Generate
- Implementation:Vespa engine Vespa KStemmer Stem
- Implementation:Allenai Open instruct Benchmark Generators
- Implementation:Datahub project Datahub Docker CLI Check
Heuristics
- Heuristic:Wandb Weave Retry And Error Handling
- Heuristic:CrewAIInc CrewAI LLM Provider Message Workarounds
- Heuristic:OpenHands OpenHands Redis Distributed Locking
- Heuristic:ARISE Initiative Robomimic Rollout Horizon Selection
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:Iterative Dvc Run Cache Restoration Strategy
- Heuristic:Ggml org Llama cpp Quantization Quality Tips
- Heuristic:OpenRLHF OpenRLHF Packing Samples Efficiency Tip
- Heuristic:Apache Beam Thread Pool Parallelism Sizing
- Heuristic:Huggingface Open r1 Reward Function Tuning
Environments
- Environment:DevExpress Testcafe Docker Xvfb Container
- Environment:Huggingface Optimum GPTQ Quantization Environment
- Environment:Mlc ai Web llm Node Build Toolchain
- Environment:Truera Trulens Python Core Environment
- Environment:Huggingface Trl DeepSpeed Environment
- Environment:Apache Druid Druid Cluster Api
- Environment:Vllm project Vllm CUDA
- Environment:Ray project Ray CI Build Matrix Environment
- Environment:Pyro ppl Pyro Distributed Training
- Environment:Microsoft Onnxruntime Python Inference Environment