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:TobikoData Sqlmesh Environment management
- Workflow:Microsoft Agent framework Agent With Tool Approval
- Workflow:EvolvingLMMs Lab Lmms eval Distributed Multi GPU Evaluation
- Workflow:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:Hiyouga LLaMA Factory DPO Preference Alignment
- Workflow:Protectai Modelscan CLI Model Scanning
- Workflow:Sail sg LongSpec Speculative Decoding Inference
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Lance format Lance Table Optimization
- Workflow:LLMBook zh LLMBook zh github io DPO Alignment
Principles
- Principle:Farama Foundation Gymnasium Composite Space Types
- Principle:OpenRLHF OpenRLHF PPO Policy Loss
- Principle:DistrictDataLabs Yellowbrick Text Feature Visualization
- Principle:OpenRLHF OpenRLHF Prompt Dataset Construction
- Principle:Ray project Ray Release Validation Testing
- Principle:PacktPublishing LLM Engineers Handbook Evaluation Results Aggregation
- Principle:Lm sys FastChat Arena Battle UI
- Principle:Norrrrrrr lyn WAInjectBench Image Feature Extraction
- Principle:ARISE Initiative Robomimic Dataset Loading
- Principle:Kserve Kserve OpenAI Compatible Inference
Implementations
- Implementation:Bentoml BentoML Models Push Pull
- Implementation:Evidentlyai Evidently ClassificationQuality Preset
- Implementation:Scikit learn Scikit learn PartialDependenceDisplay
- Implementation:FlowiseAI Flowise RBACButtons
- Implementation:CrewAIInc CrewAI RAG PDF Loader
- Implementation:Explodinggradients Ragas NoiseSensitivity Metric
- Implementation:Recommenders team Recommenders SUM Model
- Implementation:OpenHands OpenHands SaaSExperimentManager
- Implementation:Treeverse LakeFS SetGCRules
- Implementation:Ggml org Llama cpp Fit Params
Heuristics
- Heuristic:Webdriverio Webdriverio Exponential Backoff Retry
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Langchain ai Langgraph Checkpointer Selection Guide
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:Treeverse LakeFS Warning Deprecated InternalApi Methods
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Deepset ai Haystack Pipeline Deep Copy Safety
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
- Heuristic:Mage ai Mage ai HTTP Request Timeout Defaults
- Heuristic:Huggingface Alignment handbook EOS Token Alignment
Environments
- Environment:Fastai Fastbook Python FastAI Environment
- Environment:Huggingface Datasets Python PyArrow Core
- Environment:Trailofbits Fickling PyTorch
- Environment:Sgl project Sglang Triton
- Environment:Facebookresearch Audiocraft AudioCraft Environment Variables
- Environment:Mage ai Mage ai Python 3 9 Runtime
- Environment:Kserve Kserve Python Runtime
- Environment:FMInference FlexLLMGen NVMe Disk
- Environment:Huggingface Peft Python Core Dependencies
- Environment:MaterializeInc Materialize Dbt Materialize Runtime