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:Openai Openai node Chat Completion
- Workflow:Cypress io Cypress Binary Build and Release
- Workflow:Openai Openai python Chat Completion
- Workflow:Farama Foundation Gymnasium Vectorized Environment Training
- Workflow:Sdv dev SDV Sequential data synthesis
- Workflow:Wandb Weave SDK Release
- Workflow:Sdv dev SDV Multi table synthesis
- Workflow:Ggml org Llama cpp Text Generation
- Workflow:Langchain ai Langchain Tool Calling Structured Output
- Workflow:OpenGVLab InternVL Multi Stage Pretraining
Principles
- Principle:Tensorflow Serving Loader Abstraction
- Principle:Kserve Kserve PD Scheduler Routing
- Principle:Huggingface Datasets PyTorch DataLoader Integration
- Principle:Duckdb Duckdb Build Environment Setup
- Principle:PacktPublishing LLM Engineers Handbook Quantized Model Loading
- Principle:Apache Paimon Indexed Split Result Retrieval
- Principle:Helicone Helicone Legal Compliance
- Principle:Teamcapybara Capybara Selector Modification
- Principle:Ggml org Llama cpp Context Extension
- Principle:Bigscience workshop Petals Health Monitoring
Implementations
- Implementation:Microsoft DeepSpeedExamples Text Generation Test
- Implementation:Vibrantlabsai Ragas SimplePrompt
- Implementation:Ucbepic Docetl Directive AgentUtils
- Implementation:Open compass VLMEvalKit OlmOCRBench Katex Render
- Implementation:Lance format Lance LanceNamespaceTrait
- Implementation:Huggingface Diffusers ModelMixin From Pretrained Frozen
- Implementation:EvolvingLMMs Lab Lmms eval logging utils
- Implementation:Roboflow Rf detr Save GT Predictions Visualization
- Implementation:Alibaba MNN FlatBuffers IDL Gen Lobster
- Implementation:CrewAIInc CrewAI Oxylabs Amazon Search Tool
Heuristics
- Heuristic:Isaac sim IsaacGymEnvs Determinism Performance Tradeoff
- Heuristic:Cypress io Cypress Global Install Warning
- Heuristic:Togethercomputer Together python Retry Backoff Strategy
- Heuristic:NVIDIA NeMo Curator Semantic Dedup Cluster Sizing
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Avdvg InjectGuard Embedding Normalization Cosine Equivalence
- Heuristic:Langchain ai Langgraph Checkpointer Selection Guide
- Heuristic:DistrictDataLabs Yellowbrick Matplotlib rcParams Management
- Heuristic:Obss Sahi Match Threshold Tuning
- Heuristic:Spcl Graph of thoughts Scoring With Error Counting
Environments
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Fastai Fastbook Python FastAI Environment
- Environment:Astronomer Astronomer cosmos Python Airflow Runtime
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Onnx Onnx Cpp Build Environment
- Environment:Anthropics Anthropic sdk python GCP Vertex Environment
- Environment:Intel Ipex llm RAG LlamaIndex Environment
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:Pola rs Polars Cloud Storage Environment
- Environment:ARISE Initiative Robomimic PyTorch CUDA Environment