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:Lakeraai Pint benchmark Hugging Face Model Evaluation
- Workflow:CarperAI Trlx ILQL Offline Training
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:Confident ai Deepeval End to End LLM Evaluation
- Workflow:Getgauge Taiko Form Interaction Testing
- Workflow:Explodinggradients Ragas Agent Evaluation
- Workflow:Romsto Speculative Decoding Ngram Assisted Speculative Decoding
- Workflow:Dagster io Dagster RAG Pipeline
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:Ucbepic Docetl Python API Pipeline
Principles
- Principle:Microsoft BIPIA Model Loading
- Principle:InternLM Lmdeploy AWQ Weight Quantization
- Principle:Run llama Llama index Finetuned Model Integration
- Principle:NVIDIA NeMo Aligner Hydra Training Configuration
- Principle:FMInference FlexLLMGen Autotuning Configuration Search
- Principle:Risingwavelabs Risingwave Iceberg Catalog Operations
- Principle:Vespa engine Vespa Text Transformation
- Principle:FlagOpen FlagEmbedding Hard Negative Mining
- Principle:Haosulab ManiSkill CPU GPU Dual Backend
- Principle:ContextualAI HALOs Policy Sampling
Implementations
- Implementation:Evidentlyai Evidently Legacy Base Suite
- Implementation:Langchain ai Langchain Pre Release Checks
- Implementation:Farama Foundation Gymnasium Vector Observation Wrappers
- Implementation:Online ml River Datasets Keystroke
- Implementation:ArroyoSystems Arroyo Create Profile Page
- Implementation:Open compass VLMEvalKit mPLUG Owl3
- Implementation:Langfuse Langfuse API Metrics Schema
- Implementation:Apache Dolphinscheduler IWorkflowControlClient Recovery
- Implementation:CrewAIInc CrewAI AI Mind Tool
- Implementation:Apache Spark Kubectl Auth Check
Heuristics
- Heuristic:Spotify Luigi Streaming MapReduce Processing
- Heuristic:Sdv dev SDV HMA Schema Simplification
- Heuristic:Eric mitchell Direct preference optimization Activation Checkpointing Memory
- Heuristic:Cohere ai Cohere python Warning Deprecated Legacy Generate API
- Heuristic:Langgenius Dify Env Sync Upgrade Strategy
- Heuristic:Astronomer Astronomer cosmos Deprecation Migration Paths
- Heuristic:Unstructured IO Unstructured Strategy Fallback Chain
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:OWASP Www project top 10 for large language model applications Deliberately Insecure Code Isolation
- Heuristic:Zai org CogVideo Data Preparation Best Practices
Environments
- Environment:Cypress io Cypress Linux Display Server
- Environment:SeldonIO Seldon core Docker Compose Local Environment
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:Kserve Kserve Gateway API
- Environment:Microsoft DeepSpeedExamples ZeRO Inference Runtime
- Environment:Dotnet Machinelearning Platform Architecture Support
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Microsoft Onnxruntime CPU Training Environment
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Sdv dev SDV Python Runtime