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:Getgauge Taiko Form Interaction Testing
- Workflow:Apache Shardingsphere Dynamic Rule Configuration Change
- Workflow:Haifengl Smile SQL Analytics Pipeline
- Workflow:Huggingface Trl Reward Model Training
- Workflow:Langchain ai Langgraph Functional API Workflow
- Workflow:Google research Deduplicate text datasets Single file deduplication
- Workflow:Junyanz Pytorch CycleGAN and pix2pix CycleGAN Training
- Workflow:Haotian liu LLaVA Web Demo Deployment
- Workflow:Recommenders team Recommenders News Recommendation NRMS
- Workflow:Togethercomputer Together python Image Generation
Principles
- Principle:InternLM Lmdeploy Batch Text Generation
- Principle:Neuml Txtai Document Collection
- Principle:OpenRLHF OpenRLHF Optimizer and Scheduler Setup
- Principle:Facebookresearch Habitat lab Registry Registration
- Principle:Apache Druid Source Type Selection
- Principle:Helicone Helicone Verification and Testing
- Principle:Ggml org Ggml Neural Network Graph Building
- Principle:Apache Shardingsphere Column Based Routing
- Principle:Langgenius Dify PromptEngineering
- Principle:Togethercomputer Together python Speech To Text
Implementations
- Implementation:Langfuse Langfuse ProcessEventBatch
- Implementation:Isaac sim IsaacGymEnvs Factory Schema Config Hierarchy
- Implementation:FMInference FlexLLMGen HELM Install
- Implementation:Marker Inc Korea AutoRAG Make Basic Gen Gt
- Implementation:SeleniumHQ Selenium Closure UI SelectionModel
- Implementation:FlowiseAI Flowise ValidationPopUp
- Implementation:Online ml River Optim AMSGrad
- Implementation:Online ml River Datasets Keystroke
- Implementation:Scikit learn Scikit learn Ridge
- Implementation:Run llama Llama index GraphStore Types
Heuristics
- Heuristic:Spotify Luigi PySpark Task Serialization
- Heuristic:Obss Sahi Warning Deprecated Legacy NMS
- Heuristic:NVIDIA TransformerEngine Sequence Length Alignment
- Heuristic:NVIDIA NeMo Aligner DPO Sequence Packing Tips
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:NVIDIA NeMo Aligner PPO Critic Warmup Tip
- Heuristic:PeterL1n BackgroundMattingV2 Data Augmentation Strategy
- Heuristic:ChenghaoMou Text dedup Mersenne Prime Backward Compatibility
- Heuristic:Openai Openai node Retry Backoff Configuration
Environments
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:ThreeSR Awesome Inference Time Scaling Semantic Scholar API Environment
- Environment:Intel Ipex llm Portable Environment
- Environment:Openai Whisper Numba
- Environment:Apache Spark Kubernetes Runtime
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Apache Kafka Release Toolchain Environment
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Openai Openai agents python MCP Dependencies