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:Getgauge Taiko Headless Browser Testing
- Workflow:PeterL1n BackgroundMattingV2 Video matting inference
- Workflow:Haifengl Smile Nearest Neighbor Search
- Workflow:InternLM Lmdeploy LLM Offline Batch Inference
- Workflow:Huggingface Alignment handbook QLoRA Single GPU Finetuning
- Workflow:TA Lib Ta lib python Installation And Setup
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Interpretml Interpret EBM Training And Prediction
- Workflow:Microsoft Onnxruntime Train Convert Predict
- Workflow:Microsoft Semantic kernel Process Orchestration
Principles
- Principle:DataExpert io Data engineer handbook Aggregation Transformation
- Principle:Protectai Modelscan Model Security Scanning
- Principle:Vespa engine Vespa Embedding Generation
- Principle:Scikit learn contrib Imbalanced learn Sampler Aware Pipeline
- Principle:BerriAI Litellm Cache Key Generation
- Principle:Truera Trulens LangGraph Agent Construction
- Principle:CrewAIInc CrewAI Task Definition
- Principle:Helicone Helicone Data Export
- Principle:Microsoft Onnxruntime Training Artifact Generation
- Principle:MarketSquare Robotframework browser Keyword Method Implementation
Implementations
- Implementation:Avhz RustQuant ActivationFunctions
- Implementation:Microsoft Onnxruntime CheckpointState Load
- Implementation:Cleanlab Cleanlab Regression CleanLearning
- Implementation:Sgl project Sglang CPU Extend Attention
- Implementation:Huggingface Datasets Compression Filesystems
- Implementation:Anthropics Anthropic sdk python Messages Create With Thinking
- Implementation:Tensorflow Tfjs Core Layers Test
- Implementation:Apache Paimon PrimaryKeyTableSplitGenerator
- Implementation:Speechbrain Speechbrain Get Verification Scores
- Implementation:Lance format Lance EncodingsIo
Heuristics
- Heuristic:Princeton nlp Tree of thought llm Functools Partial Model Binding
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:FMInference FlexLLMGen Sequence Length Alignment
- Heuristic:Isaac sim IsaacGymEnvs DR Setup Only Flag
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:HKUDS AI Trader Position File Locking
- Heuristic:Infiniflow Ragflow Embedding Batch Size Constraint
- Heuristic:Microsoft DeepSpeedExamples RLHF Stability Constraints
- Heuristic:Puppeteer Puppeteer Navigation Race Condition Avoidance
- Heuristic:OpenRLHF OpenRLHF Adam Offload Memory Tip
Environments
- Environment:EvolvingLMMs Lab Lmms eval API Credentials Environment
- Environment:Mage ai Mage ai Python 3 9 Runtime
- Environment:Openai Openai python Azure OpenAI
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Run llama Llama index Fsspec Remote Storage
- Environment:Duckdb Duckdb Extension Distribution Env
- Environment:Vllm project Vllm AMD ROCm
- Environment:Vespa engine Vespa FNET Transport Config
- Environment:Huggingface Optimum Tensor Parallelization Environment
- Environment:Huggingface Transformers PEFT Adapter Env