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:Lucidrains X transformers Encoder Decoder Sequence to Sequence
- Workflow:Predibase Lorax Server Deployment
- Workflow:Openai Evals Implementing a custom completion function
- Workflow:TobikoData Sqlmesh Incremental model development
- Workflow:Togethercomputer Together python Batch Inference
- Workflow:Dagster io Dagster RAG Pipeline
- Workflow:Microsoft BIPIA Black Box Defense Evaluation
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Kserve Kserve Canary Rollout Deployment
- Workflow:Mlflow Mlflow GenAI Evaluation
Principles
- Principle:Cypress io Cypress Configuration Validation
- Principle:Sail sg LongSpec Environment Setup
- Principle:Huggingface Datasets Column Renaming
- Principle:Puppeteer Puppeteer Page Navigation
- Principle:Ggml org Llama cpp CLI Configuration
- Principle:Ggml org Ggml Model Quantization
- Principle:Apache Flink Compacted Committable Emission
- Principle:Apache Beam Result Commitment
- Principle:MarketSquare Robotframework browser JavaScript Module Authoring
- Principle:Spcl Graph of thoughts Keyword Counting Prompt Design
Implementations
- Implementation:TobikoData Sqlmesh Routes
- Implementation:Puppeteer Puppeteer Browser Close
- Implementation:Anthropics Anthropic sdk python MessageBatch
- Implementation:LMCache LMCache Mooncake Lookup Client
- Implementation:Microsoft Playwright Client JSHandle
- Implementation:LaurentMazare Tch rs Neural Style Transfer
- Implementation:Marker Inc Korea AutoRAG Run Node Line
- Implementation:Speechbrain Speechbrain Hparams Switchboard Transformer LM
- Implementation:NVIDIA NeMo Curator FilePartitioningStage
- Implementation:Onnx Onnx Tensor Class
Heuristics
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Deepspeedai DeepSpeed Shared Memory Sizing
- Heuristic:Run llama Llama index Evaluator LLM Selection
- Heuristic:Google deepmind Mujoco Mesh Quality For Collision
- Heuristic:Huggingface Alignment handbook Sequence Packing Strategy
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:Hpcaitech ColossalAI CUDA Device Max Connections Tip
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
- Heuristic:Danijar Dreamerv3 Symlog TwoHot Prediction
Environments
- Environment:Ucbepic Docetl LLM API Keys
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Sdv dev SDV GPU CUDA Support
- Environment:Getgauge Taiko Chromium Browser
- Environment:Huggingface Alignment handbook Python TRL
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Promptfoo Promptfoo Provider API Keys
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:BerriAI Litellm Python Runtime