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:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:Mage ai Mage ai Building a New Destination Connector
- Workflow:Spotify Luigi Hadoop MapReduce Pipeline
- Workflow:ClickHouse ClickHouse Running Stateless Tests
- Workflow:Langfuse Langfuse Prompt management lifecycle
- Workflow:Microsoft Agent framework Agent With Tool Approval
- Workflow:Apache Paimon Blob Storage With Descriptors
- Workflow:NVIDIA NeMo Aligner Supervised Fine Tuning
- Workflow:Vllm project Vllm Vision Language Inference
Principles
- Principle:Vespa engine Vespa Indexing Expression Execution
- Principle:Hpcaitech ColossalAI Ray Weight Synchronization
- Principle:Pytorch Serve Speech Recognition Inference
- Principle:AUTOMATIC1111 Stable diffusion webui Startup Performance Profiling
- Principle:Farama Foundation Gymnasium Action Transformation
- Principle:MaterializeInc Materialize Release Completion
- Principle:Datahub project Datahub Pipeline Execution
- Principle:Microsoft Playwright Extract Data with Agent
- Principle:Iterative Dvc Vega Lite Conversion
- Principle:Run llama Llama index Finetuned Model Integration
Implementations
- Implementation:NVIDIA NeMo Curator IDGenerator
- Implementation:Webdriverio Webdriverio WebDriverRequestError
- Implementation:DataTalksClub Data engineering zoomcamp Pandas Chunked CSV Loading
- Implementation:Hpcaitech ColossalAI CustomStuffDocumentsChain
- Implementation:FlowiseAI Flowise CloudMenuList
- Implementation:NVIDIA TransformerEngine Float8CurrentScaling Recipe
- Implementation:FlagOpen FlagEmbedding Matryoshka Mistral Model Inference
- Implementation:Infiniflow Ragflow GenerateButtonHook
- Implementation:EvolvingLMMs Lab Lmms eval Baseline Registry
- Implementation:OpenHands OpenHands LinearView
Heuristics
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:Liu00222 Open Prompt Injection Defense Strategy Selection
- Heuristic:MaterializeInc Materialize Pipeline Test Trimming Rules
- Heuristic:Marker Inc Korea AutoRAG One Dataset Per Project Directory
- Heuristic:Openai Openai node Retry Backoff Configuration
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Before Split Leakage
- Heuristic:Lucidrains X transformers Numerical Stability Techniques
- Heuristic:Obss Sahi Overlap Ratio Selection
- Heuristic:Apache Spark Hardware Provisioning Tips
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
Environments
- Environment:Google deepmind Dm control GLFW Desktop Rendering
- Environment:Ucbepic Docetl LLM API Keys
- Environment:Vllm project Vllm GitHub
- Environment:Volcengine Verl SGLang Rollout Environment
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:Marker Inc Korea AutoRAG API Keys Configuration
- Environment:Nightwatchjs Nightwatch Selenium WebDriver 4
- Environment:Unslothai Unsloth CUDA BitsAndBytes
- Environment:DataExpert io Data engineer handbook Statsig API Environment
- Environment:BerriAI Litellm Observability Stack