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:Tensorflow Tfjs Transfer Learning
- Workflow:ContextualAI HALOs Offline SFT Alignment Pipeline
- Workflow:Langfuse Langfuse Dataset experiment pipeline
- Workflow:Microsoft Autogen Swarm Agent Handoff
- Workflow:Nautechsystems Nautilus trader Strategy development
- Workflow:Apache Flink File Sink Pipeline
- Workflow:ClickHouse ClickHouse Packaging For Distribution
- Workflow:Haosulab ManiSkill Custom Task Development
- Workflow:Tensorflow Tfjs GPT2 Text Generation
- Workflow:Mlc ai Mlc llm REST API Serving
Principles
- Principle:Deepspeedai DeepSpeed Accelerator Abstraction
- Principle:Nightwatchjs Nightwatch Core Type System
- Principle:Iterative Dvc Experiment Apply Or Discard
- Principle:Apache Kafka Topic Deletion
- Principle:AnswerDotAI RAGatouille In Memory Search
- Principle:Ggml org Llama cpp Parallel Request Handling
- Principle:Ollama Ollama APIDesign
- Principle:Mlc ai Web llm Chrome Extension Manifest
- Principle:Pyro ppl Pyro Mixed Effect HMM
- Principle:LMCache LMCache Engine Lifecycle Management
Implementations
- Implementation:Microsoft Onnxruntime TrainingRunner Run
- Implementation:Vllm project Vllm CPU Fused MoE
- Implementation:Apache Druid GroupingTableModule
- Implementation:Scikit learn Scikit learn NumpyDocScrape
- Implementation:Elevenlabs Elevenlabs python RawBaseClient
- Implementation:Huggingface Datasets DatasetBuilder Download and Prepare
- Implementation:Infiniflow Ragflow SearchService Update By Id
- Implementation:Apache Druid AsyncActionDialog
- Implementation:Langchain ai Langchain ChatOpenAI Constructor For Streaming
- Implementation:InternLM Lmdeploy XgrammarBind
Heuristics
- Heuristic:Openai CLIP L2 Normalization For Cosine Similarity
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Identity Loss Color Preservation
- Heuristic:Microsoft Playwright Timeout Configuration Tips
- Heuristic:Openai Openai agents python MCP Server Lifecycle Management
- Heuristic:Cohere ai Cohere python Pydantic V1 V2 Compatibility
- Heuristic:Danijar Dreamerv3 Percentile Return Normalization
- Heuristic:Huggingface Alignment handbook QLoRA Learning Rate Scaling
- Heuristic:Liu00222 Open Prompt Injection Cosine Similarity Segmentation Threshold
- Heuristic:Duckdb Duckdb Sanitizer Configuration
- Heuristic:Teamcapybara Capybara Negative Predicate Matching
Environments
- Environment:Sgl project Sglang CUDA
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Axolotl ai cloud Axolotl Python Runtime
- Environment:Openai CLIP Python Dependencies
- Environment:Astronomer Astronomer cosmos Cloud Provider Dependencies
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Ucbepic Docetl Python Runtime
- Environment:Openai Evals Optional Provider APIs
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment