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:Spcl Graph of thoughts GoT Keyword Counting Pipeline
- Workflow:Haotian liu LLaVA Benchmark Evaluation
- Workflow:Datahub project Datahub Java SDK Metadata Emission
- Workflow:OpenRLHF OpenRLHF Knowledge Distillation
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:Pytorch Serve Model Deployment
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Entry Development
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Diagram of thought Diagram of thought DoT Iterative Reasoning
Principles
- Principle:Cypress io Cypress Binary Installation
- Principle:Tensorflow Serving TFRT Inference
- Principle:Tencent Ncnn Non Maximum Suppression
- Principle:Recommenders team Recommenders Chronological Data Splitting
- Principle:Huggingface Transformers Fully Sharded Data Parallelism
- Principle:NVIDIA TransformerEngine Fused LayerNorm MLP
- Principle:Openai Evals Result Aggregation
- Principle:Scikit learn Scikit learn Online Learning
- Principle:NVIDIA TransformerEngine Layer Monkey Patching
- Principle:Apache Spark Test Orchestration
Implementations
- Implementation:Ollama Ollama Llama Quant
- Implementation:Webdriverio Webdriverio Cloud Capabilities Config
- Implementation:Openai Openai python Easy Input Message Param
- Implementation:Protectai Llm guard Vault
- Implementation:Apache Paimon FunctionDefinition
- Implementation:Microsoft DeepSpeedExamples LLaMA Tensor Parallel Finetuning
- Implementation:Mlc ai Mlc llm Metrics Impl
- Implementation:Apache Paimon StringUtils
- Implementation:Mlc ai Mlc llm Qwen3 Model
- Implementation:Microsoft DeepSpeedExamples Named Tuple Batch Handling
Heuristics
- Heuristic:Neuml Txtai Batch Size Defaults
- Heuristic:Openai Openai python Fine Tuning Data Preparation Tips
- Heuristic:NVIDIA NeMo Aligner DPO Sequence Packing Tips
- Heuristic:Hiyouga LLaMA Factory Gradient Checkpointing Memory Optimization
- Heuristic:Microsoft Onnxruntime Memory Recomputation Optimization
- Heuristic:Langchain ai Langgraph Durability Mode Selection
- Heuristic:Openclaw Openclaw Retry With Exponential Backoff
- Heuristic:Avdvg InjectGuard Module Level Initialization
- Heuristic:AUTOMATIC1111 Stable diffusion webui NaN Detection And Precision Fixes
- Heuristic:HKUDS AI Trader DeepSeek Tool Args Workaround
Environments
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Apache Paimon Python Core Runtime
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:TobikoData Sqlmesh Python Runtime
- Environment:Testtimescaling Testtimescaling github io Semantic Scholar API
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Dagster io Dagster DAGSTER HOME Configuration
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:Haosulab ManiSkill Real Robot LeRobot Deps