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:Huggingface Datatrove Synthetic Data Generation
- Workflow:Mbzuai oryx Awesome LLM Post training Research Trend Analysis
- Workflow:Mlc ai Web llm Function Calling
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:DataTalksClub Data engineering zoomcamp dlt Data Ingestion
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:Danijar Dreamerv3 Distributed Parallel Training
- Workflow:OpenBMB UltraFeedback GPT4 Preference Annotation
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
- Workflow:Apache Hudi Docker Demo Setup
Principles
- Principle:Farama Foundation Gymnasium Interactive Human Play
- Principle:ClickHouse ClickHouse Stateless Test Execution
- Principle:Cleanlab Cleanlab Identifier Column Issue Detection
- Principle:Kserve Kserve Multi Model Prediction
- Principle:PrefectHQ Prefect Flow Run Querying
- Principle:Scikit learn contrib Imbalanced learn Borderline Oversampling
- Principle:Kornia Kornia Image Stitching
- Principle:Webdriverio Webdriverio BrowserStack Capability Management
- Principle:Iamhankai Forest of Thought Chain of Thought Reasoning
- Principle:Cleanlab Cleanlab Regression Label Quality Scoring
Implementations
- Implementation:SeldonIO Seldon core Seldon Pipeline CRD Multi Modal
- Implementation:Evidentlyai Evidently Legacy Data Drift Preset
- Implementation:Risingwavelabs Risingwave ElasticBulkProcessorAdapter
- Implementation:Langchain ai Langgraph Pregel Algo
- Implementation:LaurentMazare Tch rs Stb Image
- Implementation:NVIDIA TransformerEngine JAX Attention
- Implementation:Cohere ai Cohere python BatchesClient
- Implementation:Eventual Inc Daft DataFrame Where
- Implementation:Online ml River Anomaly SAD
- Implementation:Microsoft Autogen Studio Generate Image Tool
Heuristics
- Heuristic:Cohere ai Cohere python Embed Auto Batching Strategy
- Heuristic:EvolvingLMMs Lab Lmms eval Bootstrap Iteration Optimization
- Heuristic:Huggingface Diffusers Dtype Precision Selection
- Heuristic:Dagster io Dagster Lazy Import Pattern
- Heuristic:Mistralai Client python Retry Backoff Strategy
- Heuristic:Unstructured IO Unstructured Warning Deprecated Staging Base
- Heuristic:NVIDIA NeMo Aligner Warning Deprecated Repository
- Heuristic:Microsoft LoRA Label Smoothing NLG
- Heuristic:InternLM Lmdeploy KV Quantization Tradeoffs
- Heuristic:Mit han lab Llm awq Skip QK Projection Clipping
Environments
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:DataTalksClub Data engineering zoomcamp Kestra Orchestration Environment
- Environment:Apache Beam Dataflow Streaming Runtime
- Environment:Langchain ai Langchain Unit Test Network Isolation
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Explodinggradients Ragas Python Runtime Environment
- Environment:DataTalksClub Data engineering zoomcamp Docker PostgreSQL Python Environment
- Environment:Spcl Graph of thoughts OpenAI API Access
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:Sdv dev SDV GPU CUDA Support