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:Mlc ai Web llm Structured Output Generation
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:SeldonIO Seldon core Production Monitoring Pipeline
- Workflow:Vespa engine Vespa CI CD build pipeline
- Workflow:Protectai Llm guard LLM Input Output Scanning
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
- Workflow:OpenRLHF OpenRLHF PPO Ray Training
- Workflow:Apache Flink File Sink Pipeline
- Workflow:Ggml org Ggml Model Conversion And Quantization
- Workflow:Huggingface Transformers 3D Parallel Distributed Training
Principles
- Principle:Heibaiying BigData Notes MapReduce Combiner
- Principle:MarketSquare Robotframework browser ES2015 Module Transpilation
- Principle:Huggingface Datasets Text Dataset Building
- Principle:Bigscience workshop Petals Distributed Model Loading
- Principle:Tencent Ncnn Hardware Capability Detection
- Principle:SeldonIO Seldon core Model Lifecycle Management
- Principle:Mlc ai Web llm Tool Call Extraction
- Principle:Shiyu coder Kronos Predictor Finetuning
- Principle:Huggingface Datasets Row Count Inspection
- Principle:Online ml River Tree Split Strategies
Implementations
- Implementation:Open compass VLMEvalKit ScreenSpot Pro
- Implementation:Scikit learn Scikit learn EllipticEnvelope
- Implementation:Hpcaitech ColossalAI Math Competition Reward
- Implementation:Online ml River Datasets TrumpApproval
- Implementation:Neuml Txtai M2V Vectors
- Implementation:Cleanlab Cleanlab TC Find Label Issues
- Implementation:ARISE Initiative Robomimic Algo factory
- Implementation:Dagster io Dagster DagsterDbtTranslator API
- Implementation:Huggingface Optimum Compose
- Implementation:Pytorch Serve Intel GPU Utils
Heuristics
- Heuristic:Tensorflow Serving Resource Estimation Rules
- Heuristic:Treeverse LakeFS Presigned URL Expiry Tip
- Heuristic:ChenghaoMou Text dedup Fingerprint Batch Size One
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:Langfuse Langfuse LLM Rate Limit 24h Abandon
- Heuristic:Apache Shardingsphere Shadow Routing Hint First Fallback
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:Langgenius Dify Credential Sanitization In API Responses
- Heuristic:Datahub project Datahub Validation Across All APIs
Environments
- Environment:Sgl project Sglang ROCm
- Environment:Unstructured IO Unstructured GitHub Actions
- Environment:Risingwavelabs Risingwave Python Tooling Environment
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:HKUDS AI Trader Python LangChain Runtime
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:FMInference FlexLLMGen HuggingFace Access
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:Facebookresearch Audiocraft Python PyTorch CUDA Environment