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:Facebookresearch Habitat lab HITL Interactive Evaluation
- Workflow:MarketSquare Robotframework browser Library Development and Release
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Princeton nlp Tree of thought llm Baseline comparison
- Workflow:Norrrrrrr lyn WAInjectBench LLaVA Finetuning
- Workflow:Eventual Inc Daft Multimodal AI Batch Inference
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:CARLA simulator Carla Simulation Recording and Replay
- Workflow:Interpretml Interpret EBM Model Merging
- Workflow:DevExpress Testcafe CI Integration
Principles
- Principle:Open compass VLMEvalKit Dataset Base Class Hierarchy
- Principle:Datajuicer Data juicer Data Processing Execution
- Principle:Ggml org Llama cpp Constrained Generation
- Principle:LLMBook zh LLMBook zh github io DPO Model Loading
- Principle:Gretelai Gretel synthetics Batch Synthetic Generation
- Principle:Langgenius Dify Application Publishing
- Principle:Nightwatchjs Nightwatch Custom Assertion Creation
- Principle:PacktPublishing LLM Engineers Handbook Supervised Finetuning
- Principle:NVIDIA NeMo Curator Connected Component Analysis
- Principle:Huggingface Trl GRPO Argument Configuration
Implementations
- Implementation:Datahub project Datahub DatahubEventEmitter Emit
- Implementation:Volcengine Verl HH RLHF Data Preprocessing
- Implementation:Neuml Txtai Subindex Manager
- Implementation:Explodinggradients Ragas Amazon Bedrock Integration
- Implementation:Haotian liu LLaVA Train Stage1 Pretrain
- Implementation:NVIDIA TransformerEngine JAX Cpp Normalization
- Implementation:BerriAI Litellm Responses Utils
- Implementation:Open compass VLMEvalKit GLMVisionWrapper
- Implementation:NVIDIA NeMo Curator QwenVL
- Implementation:Scikit learn Scikit learn FactorAnalysis
Heuristics
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Pytorch Serve CPU Performance Tuning
- Heuristic:Duckdb Duckdb Unity Build Strategy
- Heuristic:ClickHouse ClickHouse ThinLTO Build Tradeoffs
- Heuristic:Guardrails ai Guardrails Sentence Tokenizer Optimization
- Heuristic:Sdv dev SDV Gaussian KDE Incompatibility
- Heuristic:Fastai Fastbook Discriminative Learning Rates
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
Environments
- Environment:Huggingface Open r1 vLLM Server
- Environment:Arize ai Phoenix LLM Provider SDKs
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Intel Ipex llm CPU Finetuning Environment
- Environment:Gretelai Gretel synthetics TensorFlow GPU Environment
- Environment:CrewAIInc CrewAI LLM Provider Credentials
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:Huggingface Datasets Lance Dependencies
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Unstructured IO Unstructured All Docs