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:Helicone Helicone LLM Response Normalization
- Workflow:Cleanlab Cleanlab Datalab Dataset Audit
- Workflow:Eventual Inc Daft Distributed UDF Processing
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:Puppeteer Puppeteer Cross Browser Automation
- Workflow:Farama Foundation Gymnasium RL Agent Training Loop
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Zai org CogVideo SAT Finetuning
- Workflow:Vespa engine Vespa Logging framework initialization
- Workflow:Infiniflow Ragflow Document Processing Pipeline
Principles
- Principle:Microsoft Autogen Component Serialization
- Principle:Apache Spark Application Entry Point
- Principle:HKUDS AI Trader Frontend Data Loading
- Principle:OpenRLHF OpenRLHF Process Reward Model Training
- Principle:TobikoData Sqlmesh Dbt Project Assessment
- Principle:Huggingface Alignment handbook Direct Preference Optimization
- Principle:Tensorflow Serving Type Safe Erasure
- Principle:Webdriverio Webdriverio Reporter Pattern
- Principle:AUTOMATIC1111 Stable diffusion webui Launch Sequence
- Principle:Protectai Llm guard Topic Filtering
Implementations
- Implementation:NVIDIA TransformerEngine Ops Fused Backward Linear Scale
- Implementation:Sgl project Sglang Marlin MoE WNA16 Template
- Implementation:Ucbepic Docetl DebateContent
- Implementation:Cleanlab Cleanlab TC Display Issues
- Implementation:Microsoft LoRA Run GLUE LoRA Config
- Implementation:Fastai Fastbook Pandas Read Csv
- Implementation:Openai Evals FewShotSolver
- Implementation:Speechbrain Speechbrain Composite Eval Metrics
- Implementation:Webdriverio Webdriverio SpecReporter Utils
- Implementation:AUTOMATIC1111 Stable diffusion webui Run modelmerger
Heuristics
- Heuristic:Treeverse LakeFS Batch Delay Tuning
- Heuristic:Pola rs Polars Streaming For Large Datasets
- Heuristic:FlagOpen FlagEmbedding Same Dataset Batching Tip
- Heuristic:Farama Foundation Gymnasium Seeding Determinism Best Practices
- Heuristic:LMCache LMCache Memory Fragmentation Budget
- Heuristic:CrewAIInc CrewAI LLM Provider Message Workarounds
- Heuristic:Deepspeedai DeepSpeed ZeRO Pipeline Incompatibility
- Heuristic:Alibaba ROLL Numerical Stability Epsilon
- Heuristic:Infiniflow Ragflow Citation Threshold Decay
- Heuristic:Datajuicer Data juicer Partition Size Tuning
Environments
- Environment:Haotian liu LLaVA OpenAI API Evaluation Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Microsoft Onnxruntime Distributed Training Environment
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Marker Inc Korea AutoRAG VLLM Environment
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:Cleanlab Cleanlab Datalab Dependencies
- Environment:CarperAI Trlx DeepSpeed Multi GPU
- Environment:Openai Openai agents python Python 3 9 Runtime
- Environment:Vllm project Vllm ROCm