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:Nautechsystems Nautilus trader Strategy development
- Workflow:Mlflow Mlflow Model Serving
- Workflow:Apache Spark Building and Testing
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:Mlfoundations Open flamingo Data Preparation
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:Anthropics Anthropic sdk python Cloud Provider Deployment
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:Diagram of thought Diagram of thought DoT Iterative Reasoning
Principles
- Principle:OWASP Www project top 10 for large language model applications Agentic Mitigation Recommendations
- Principle:Unstructured IO Unstructured PDF Partitioning
- Principle:AUTOMATIC1111 Stable diffusion webui Extension Management
- Principle:LaurentMazare Tch rs BPE Tokenization
- Principle:Huggingface Datasets Dataset From Pandas Construction
- Principle:Mlc ai Mlc llm Compiled Artifact Validation
- Principle:FlowiseAI Flowise Evaluation Rerun
- Principle:AUTOMATIC1111 Stable diffusion webui Extension Architecture
- Principle:OWASP Www project top 10 for large language model applications Threat Modeling Against Top 10
- Principle:Google research Deduplicate text datasets Byte Range Removal
Implementations
- Implementation:Online ml River Anomaly Score One
- Implementation:Huggingface Peft Constants
- Implementation:Helicone Helicone Unified Types
- Implementation:Mlc ai Web llm Completion Request
- Implementation:Roboflow Rf detr Supervision Annotators
- Implementation:EvolvingLMMs Lab Lmms eval GEdit Bench YAML Config
- Implementation:Speechbrain Speechbrain SEBrain Compute Forward
- Implementation:Groq Groq python Embeddings Create
- Implementation:Lance format Lance Java CreateIndexOp
- Implementation:Explodinggradients Ragas ContextPrecision Metric
Heuristics
- Heuristic:Vespa engine Vespa Log Level Inheritance Polling
- Heuristic:Langgenius Dify Env Sync Upgrade Strategy
- Heuristic:Pola rs Polars GPU Aggregation Join Speedup
- Heuristic:Vespa engine Vespa KStemmer Dictionary Loading
- Heuristic:ChenghaoMou Text dedup SimHash Optimization Ceiling
- Heuristic:Openai Whisper No Speech Detection
- Heuristic:Princeton nlp Tree of thought llm Duplicate Candidate Zeroing
- Heuristic:PacktPublishing LLM Engineers Handbook Token Window Safety Margin
- Heuristic:Huggingface Peft RSLoRA Scaling
- Heuristic:PacktPublishing LLM Engineers Handbook DPO Training Configuration
Environments
- Environment:Google research Deduplicate text datasets Rust Cargo Build Environment
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Hpcaitech ColossalAI CUDA GPU Environment
- Environment:Obss Sahi Python Pycocotools