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:Langchain ai Langchain Chat Model Invocation
- Workflow:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:Puppeteer Puppeteer PDF Generation
- Workflow:Intel Ipex llm LoRA Finetuning
- Workflow:Googleapis Python genai Multi Turn Chat
- Workflow:Microsoft Agent framework Multi Agent Sequential Orchestration
- Workflow:Apache Airflow Scheduler Operation and Task Execution
- Workflow:Langchain ai Langchain Tool Calling Structured Output
- Workflow:BerriAI Litellm Observability Integration
- Workflow:Trailofbits Fickling Pickle Safety Analysis
Principles
- Principle:Huggingface Transformers Adapter Loading And Switching
- Principle:MaterializeInc Materialize Composition Service Definition
- Principle:CARLA simulator Carla Navigation Agent Architecture
- Principle:Risingwavelabs Risingwave CDC Change Data Capture
- Principle:Ollama Ollama KVCache Abstraction
- Principle:DistrictDataLabs Yellowbrick Knee Point Detection
- Principle:Dagster io Dagster Declarative Automation
- Principle:Cohere ai Cohere python Message Construction
- Principle:DistrictDataLabs Yellowbrick Dataset Loading
- Principle:Confident ai Deepeval Installation and Configuration
Implementations
- Implementation:Openai Whisper Transcribe Timestamp Parsing
- Implementation:Apache Paimon ResourcePaths
- Implementation:Ucbepic Docetl WebSocket Run Pipeline
- Implementation:Google deepmind Mujoco User Objects
- Implementation:EvolvingLMMs Lab Lmms eval Regression Testing
- Implementation:AUTOMATIC1111 Stable diffusion webui ScriptPostprocessingRunner run
- Implementation:Duckdb Duckdb Generate C Api
- Implementation:Hpcaitech ColossalAI ExperienceBuffer Base
- Implementation:Datajuicer Data juicer TextActionFilter
- Implementation:Microsoft Playwright Client Android
Heuristics
- Heuristic:Ggml org Llama cpp Thread Count Tuning
- Heuristic:Ggml org Ggml Gradient Accumulation Batch Sizing
- Heuristic:Dagster io Dagster Mandatory Ruff Formatting
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Allenai Open instruct Gradient Clipping Norm
- Heuristic:Huggingface Diffusers VAE Scaling Factors
- Heuristic:TobikoData Sqlmesh Forward Only Safety
- Heuristic:Protectai Llm guard Token Limit Early Guard
- Heuristic:Alibaba MNN Weight Quantization Strategy
- Heuristic:Openai Openai python Retry Backoff Strategy
Environments
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Hiyouga LLaMA Factory Optional Inference Backends
- Environment:Microsoft Semantic kernel ONNX CUDA Environment
- Environment:Arize ai Phoenix Phoenix Server Runtime
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Haotian liu LLaVA Python CUDA Training Environment
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Mlflow Mlflow GPU System Metrics Environment
- Environment:Google deepmind Dm control Python MuJoCo Runtime