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:Datahub project Datahub Docker Quickstart Deployment
- Workflow:Cohere ai Cohere python Semantic Search With Rerank
- Workflow:Pytorch Serve LLM Deployment vLLM
- Workflow:Danijar Dreamerv3 Distributed Parallel Training
- Workflow:Helicone Helicone LLM Response Normalization
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Sdv dev SDV Multi table synthesis
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:DataTalksClub Data engineering zoomcamp Spark Batch Processing
- Workflow:Openai Evals Running an eval set
Principles
- Principle:OWASP Www project top 10 for large language model applications Agentic Mitigation Recommendations
- Principle:EvolvingLMMs Lab Lmms eval Experiment Tracking
- Principle:Duckdb Duckdb Unicode Processing
- Principle:Tensorflow Tfjs Task Head Construction
- Principle:Haifengl Smile SQL to ML Bridge
- Principle:Lm sys FastChat Environment Setup
- Principle:Infiniflow Ragflow Server Startup
- Principle:Deepseek ai Janus Image Loading and Preprocessing
- Principle:Langfuse Langfuse OTel Input Output Extraction
- Principle:Mlc ai Web llm Structured Output Parsing
Implementations
- Implementation:NVIDIA DALI COCO TFRecord Creator
- Implementation:Microsoft Playwright FrameDispatcher
- Implementation:AUTOMATIC1111 Stable diffusion webui Token Counters
- Implementation:FlowiseAI Flowise NavGroup
- Implementation:Turboderp org Exllamav2 PromptFormat Interface
- Implementation:Deepspeedai DeepSpeed Initialize For SFT
- Implementation:Dotnet Machinelearning FastTree Sumup
- Implementation:Neuml Txtai TextToAudio
- Implementation:Open compass VLMEvalKit JTVLChatWrapper Mini
- Implementation:Vespa engine Vespa Feed Client API ABI Spec
Heuristics
- Heuristic:ClickHouse ClickHouse Jemalloc Production Requirement
- Heuristic:HKUDS AI Trader Sortino Ratio Capping
- Heuristic:Hiyouga LLaMA Factory LoRA DDP Configuration
- Heuristic:Togethercomputer Together python Multipart Upload Strategy
- Heuristic:Unslothai Unsloth Padding Free Packing
- Heuristic:Ucbepic Docetl Optimizer Sample Sizes
- Heuristic:Huggingface Open r1 vLLM GPU Allocation
- Heuristic:OpenRLHF OpenRLHF Off Policy IS Correction Tip
- Heuristic:Mlc ai Web llm Low Resource Model Selection
- Heuristic:Diagram of thought Diagram of thought Typed Records For Auditability
Environments
- Environment:Getgauge Taiko Chromium Browser
- Environment:Ucbepic Docetl Python Runtime
- Environment:Rapidsai Cuml Python RAPIDS Stack
- Environment:Evidentlyai Evidently Spark Engine Environment
- Environment:AUTOMATIC1111 Stable diffusion webui Xformers Attention
- Environment:Sgl project Sglang Grafana
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Kserve Kserve Cert Manager
- Environment:Neuml Txtai Python Core Dependencies
- Environment:Hiyouga LLaMA Factory Distributed Training Environment