Main Page
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:Volcengine Verl Multi Turn Tool Use Training
- Workflow:Intel Ipex llm Pipeline Parallel Inference
- Workflow:Gretelai Gretel synthetics DataFrame Batch Synthesis
- Workflow:Iterative Dvc Plot Visualization
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Langgenius Dify Knowledge Base Management
- Workflow:Langgenius Dify Plugin Installation and Configuration
- Workflow:NVIDIA NeMo Curator Text Curation Pipeline
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Guardrails ai Guardrails Server Deployment
Principles
- Principle:Microsoft Semantic kernel Search Provider Test Fixtures
- Principle:Microsoft Agent framework YAML Agent Loading
- Principle:Scikit learn Scikit learn Stacking Ensemble
- Principle:Mlc ai Web llm Web Worker Engine Proxy
- Principle:Shiyu coder Kronos Predictor Initialization
- Principle:Datajuicer Data juicer Configuration Initialization
- Principle:Marker Inc Korea AutoRAG Corpus Ingestion
- Principle:Ollama Ollama GGUF Model Conversion NomicBert
- Principle:CarperAI Trlx Hyperparameter Sweep
- Principle:Explodinggradients Ragas Knowledge Graph Enrichment
Implementations
- Implementation:ArroyoSystems Arroyo Sink V2 Open File
- Implementation:BerriAI Litellm Completion With Fine Tuned Model
- Implementation:Anthropics Anthropic sdk python ToolResultBlockParam
- Implementation:Hiyouga LLaMA Factory V1 Inference Engine
- Implementation:Haosulab ManiSkill RoboCasaStove
- Implementation:Nautechsystems Nautilus trader Strategy Cancel Close
- Implementation:Online ml River Metrics RandIndex
- Implementation:SeleniumHQ Selenium Closure ErrorHandler
- Implementation:Predibase Lorax Flash GPT2 Modeling
- Implementation:Microsoft Autogen Studio Bing Search Tool
Heuristics
- Heuristic:Speechbrain Speechbrain Separation Loss Filtering
- Heuristic:Intel Ipex llm NF4 Quantization Best Practice
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
- Heuristic:NVIDIA TransformerEngine Sequence Length Alignment
- Heuristic:Webdriverio Webdriverio Click Interception Workaround
- Heuristic:InternLM Lmdeploy Max Batch Size Selection
- Heuristic:Huggingface Trl Disable Dropout For RL Training
- Heuristic:Ggml org Ggml Gradient Accumulation Batch Sizing
- Heuristic:Protectai Llm guard PyTorch Compile Warmup
- Heuristic:FMInference FlexLLMGen Offloading Percent Tuning
Environments
- Environment:Interpretml Interpret Blackbox Explainer Dependencies
- Environment:Microsoft LoRA NLU Conda Environment
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:Kubeflow Pipelines KFP Backend Deployment
- Environment:Huggingface Optimum Accelerated Inference Environment
- Environment:Mlc ai Mlc llm OpenCL Android Environment
- Environment:Sgl project Sglang Python Dependencies
- Environment:Sgl project Sglang CUDA SM100
- Environment:Openai Whisper Numba
- Environment:Ggml org Llama cpp Vulkan GPU Environment