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 Alignment handbook ORPO Single Stage Alignment
- Workflow:Treeverse LakeFS Write Audit Publish With Hooks
- Workflow:Hiyouga LLaMA Factory Model Inference and Serving
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Openai Whisper Audio Transcription
- Workflow:Huggingface Peft QLoRA SFT Finetuning
- Workflow:PrefectHQ Prefect Dbt Model Orchestration
- Workflow:Langchain ai Langchain Chat Model Invocation
- Workflow:Apache Airflow DAG Authoring and Deployment
- Workflow:Vibrantlabsai Ragas RAG Evaluation
Principles
- Principle:Cohere ai Cohere python Finetuned Model Creation
- Principle:Risingwavelabs Risingwave Iceberg Catalog Operations
- Principle:MarketSquare Robotframework browser Custom Keyword Invocation
- Principle:Gretelai Gretel synthetics LSTM Model Building
- Principle:Eventual Inc Daft Data Display
- Principle:Helicone Helicone API Specification
- Principle:ARISE Initiative Robosuite Visual Feedback Wrapping
- Principle:Langchain ai Langchain Incremental Chunk Processing
- Principle:Webdriverio Webdriverio Component Test Rendering
- Principle:Duckdb Duckdb Enum Code Generation
Implementations
- Implementation:Huggingface Datatrove C4QualityFilter
- Implementation:Cohere ai Cohere python LogprobItem Model
- Implementation:Ggml org Ggml Cpu compute engine
- Implementation:Langfuse Langfuse Sessions UI Table Events Service
- Implementation:Scikit learn Scikit learn Score Distribution Pattern
- Implementation:Infiniflow Ragflow FloatingChatWidgetMarkdown Component
- Implementation:Arize ai Phoenix Run Experiment
- Implementation:LMCache LMCache Memory Bloom Filter Strategy
- Implementation:Turboderp org Exllamav2 Tokenize Calibration
- Implementation:ArroyoSystems Arroyo Pipelines Table
Heuristics
- Heuristic:Explodinggradients Ragas Retry And Backoff Configuration
- Heuristic:OpenRLHF OpenRLHF vLLM Embedding Resize Warning
- Heuristic:Lucidrains X transformers Numerical Stability Techniques
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:CARLA simulator Carla Behavior Agent Profiles
- Heuristic:Microsoft Onnxruntime Convergence Debugging Tips
- Heuristic:Cypress io Cypress Xvfb Display Gotcha
- Heuristic:Bigscience workshop Petals Prompt Embeddings Float32 Precision
- Heuristic:Lakeraai Pint benchmark Chunking Stride 25 Percent Overlap
- Heuristic:Zai org CogVideo DeepSpeed Checkpoint Conversion Tips
Environments
- Environment:Sgl project Sglang Python Dependencies
- Environment:ArroyoSystems Arroyo Kubernetes Deployment
- Environment:Nautechsystems Nautilus trader Databento API Credentials
- Environment:Pytorch Serve CUDA GPU Environment
- Environment:Helicone Helicone Docker Compose Infrastructure
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Unstructured IO Unstructured PDF Dependencies
- Environment:Sgl project Sglang CUDA GPU Runtime
- Environment:Kserve Kserve Python Runtime