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:FMInference FlexLLMGen Text Completion API
- Workflow:Mlc ai Mlc llm Disaggregated Serving
- Workflow:Protectai Llm guard PII Anonymization Deanonymization
- Workflow:PacktPublishing LLM Engineers Handbook LLM Finetuning
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Arize ai Phoenix Dataset and Experiment Lifecycle
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:OpenRLHF OpenRLHF Math Reasoning Training
- Workflow:Run llama Llama index Evaluation Pipeline
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
Principles
- Principle:Scikit learn Scikit learn Dimensionality Reduction
- Principle:Romsto Speculative Decoding Ngram Storage
- Principle:Huggingface Datasets Dataset Shuffling
- Principle:OpenGVLab InternVL Streamlit Chat Interface
- Principle:Togethercomputer Together python Fine Tuning Job Creation
- Principle:Bitsandbytes foundation Bitsandbytes 4bit Linear Layer
- Principle:Ollama Ollama Blob Transfer
- Principle:Interpretml Interpret Global Explanation Generation
- Principle:Diagram of thought Diagram of thought Prompt Template Selection
- Principle:Mlflow Mlflow Prompt Search and Versioning
Implementations
- Implementation:Ggml org Llama cpp Batch Header
- Implementation:Cypress io Cypress Detect Browsers
- Implementation:Online ml River ModelSelection Greedy
- Implementation:Huggingface Datasets Audio
- Implementation:CARLA simulator Carla Lane
- Implementation:Elevenlabs Elevenlabs python UnitTestSummaryResponseModel
- Implementation:Datahub project Datahub Pip Install Datahub SDK
- Implementation:Nautechsystems Nautilus trader Cargo Workspace Manifest
- Implementation:Openai Openai python API Pagination
- Implementation:Google deepmind Dm control Hooks Test Utils
Heuristics
- Heuristic:Vllm project Vllm GPU Memory Utilization Tuning
- Heuristic:OpenHands OpenHands Redis Distributed Locking
- Heuristic:Gretelai Gretel synthetics Memory Chunking For Normalization
- Heuristic:CARLA simulator Carla Client Server Version Match
- Heuristic:FlowiseAI Flowise Edge Connection Type Matching
- Heuristic:Shiyu coder Kronos Instance Normalization Clipping
- Heuristic:Ggml org Llama cpp Warning Deprecated Legacy Converters
- Heuristic:Promptfoo Promptfoo Adaptive Concurrency Tuning
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:Tencent Ncnn Letterbox Vs Direct Resize
Environments
- Environment:Ggml org Llama cpp CMake Build Environment
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment
- Environment:Lm sys FastChat Python Core Dependencies
- Environment:Apache Flink Node Build Environment
- Environment:Explodinggradients Ragas Google Drive Backend Environment
- Environment:SqueezeAILab ETS Multi GPU Sglang Runtime
- Environment:Diagram of thought Diagram of thought Python Graph Libraries
- Environment:Vllm project Vllm AWS ECR
- Environment:Promptfoo Promptfoo Browser Automation
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment