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:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Turboderp org Exllamav2 Text Generation
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
- Workflow:Openai Openai agents python Human In The Loop Approval
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:Datahub project Datahub Java SDK Metadata Emission
- Workflow:OpenHands OpenHands Organization Onboarding
- Workflow:Testtimescaling Testtimescaling github io GitHub Pages Course Progression
- Workflow:MarketSquare Robotframework browser Plugin Development
Principles
- Principle:Zai org CogVideo SAT Inference Configuration
- Principle:Apache Flink File Enumeration and Splitting
- Principle:Explodinggradients Ragas Prompt Persistence
- Principle:Datahub project Datahub Emitter Instantiation
- Principle:Apache Spark Release Finalization
- Principle:Roboflow Rf detr Training Configuration
- Principle:LMCache LMCache Prefill Decode Configuration
- Principle:ARISE Initiative Robosuite Placement Sampling
- Principle:Webdriverio Webdriverio Protocol Command Architecture
- Principle:Turboderp org Exllamav2 Multi GPU Compatibility
Implementations
- Implementation:Mlc ai Mlc llm Gemma2 Model
- Implementation:Treeverse LakeFS S3 Path Convention
- Implementation:Speechbrain Speechbrain LibriSpeech LM Dataset
- Implementation:Explodinggradients Ragas Evaluate Function
- Implementation:Langgenius Dify Service Annotation
- Implementation:Datajuicer Data juicer NestedAggregator
- Implementation:Alibaba ROLL DPO Zh Demo Dataset
- Implementation:ContextualAI HALOs Alpaca Eval CLI
- Implementation:Datahub project Datahub MetadataChangeProposalWrapper Java
- Implementation:Speechbrain Speechbrain Prepare RescueSpeech Root
Heuristics
- Heuristic:Turboderp org Exllamav2 Attention Backend Selection
- Heuristic:Langchain ai Langchain Warning Deprecated Langchain Classic
- Heuristic:Tencent Ncnn Lightmode Memory Optimization
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
- Heuristic:Allenai Open instruct BFloat16 Training
- Heuristic:Bigscience workshop Petals NF4 Quantization Default On CUDA
- Heuristic:Roboflow Rf detr Layer Wise LR Decay
- Heuristic:Diagram of thought Diagram of thought Typed Records For Auditability
- Heuristic:AnswerDotAI RAGatouille Index Rebuild Vs Update Decision
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Instance Norm for Multi GPU
Environments
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:Langfuse Langfuse S3 Compatible Storage
- Environment:Kserve Kserve Istio Service Mesh
- Environment:Bitsandbytes foundation Bitsandbytes CUDA GPU Runtime
- Environment:Openclaw Openclaw Mintlify Documentation Platform
- Environment:Langfuse Langfuse Redis 7 Queue Cache
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:Huggingface Transformers PyTorch 24 CUDA
- Environment:Kserve Kserve Leader Worker Set