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:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:Spcl Graph of thoughts GoT Document Merging Pipeline
- Workflow:NVIDIA NeMo Aligner DPO Training
- Workflow:Apache Beam Portable Pipeline Submission
- Workflow:Liu00222 Open Prompt Injection DataSentinel Detection
- Workflow:Promptfoo Promptfoo Red Team Security Scan
- Workflow:Diagram of thought Diagram of thought DoT Prompt Customization
- Workflow:Marker Inc Korea AutoRAG Pipeline Deployment
- Workflow:Onnx Onnx Model Composition
- Workflow:Deepspeedai DeepSpeed AutoTP Training
Principles
- Principle:Apache Beam Job Execution
- Principle:AUTOMATIC1111 Stable diffusion webui Model Identification
- Principle:Turboderp org Exllamav2 Model Configuration
- Principle:Alibaba ROLL Qwen3 Omni Multimodal Model
- Principle:NVIDIA TransformerEngine Complete Transformer Layer
- Principle:Open compass VLMEvalKit Dataset Registration
- Principle:Confident ai Deepeval Documentation Site Configuration
- Principle:NVIDIA NeMo Curator CLIP Embedding
- Principle:Huggingface Datatrove Parquet Data Writing
- Principle:Pyro ppl Pyro Attend Infer Repeat
Implementations
- Implementation:Online ml River Misc Skyline
- Implementation:Promptfoo Promptfoo Code Scan Package Lock
- Implementation:Apache Airflow PercentFormatRender
- Implementation:MarketSquare Robotframework browser Response Util
- Implementation:Lance format Lance Java NamespaceStorageOptions
- Implementation:Haosulab ManiSkill Humanoid
- Implementation:LLMBook zh LLMBook zh github io CleanerSubstitutePassageIDCard Clean Single Text
- Implementation:Online ml River Optim Momentum
- Implementation:Facebookresearch Habitat lab XRInput
- Implementation:Microsoft Playwright HappyEyeballs
Heuristics
- Heuristic:Ggml org Ggml Memory Allocation Strategy
- Heuristic:NVIDIA TransformerEngine FP8 Checkpoint Compatibility
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Ray project Ray NaN Score Filtering In PBT
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Gretelai Gretel synthetics Batch Size Divisibility Constraints
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
- Heuristic:CARLA simulator Carla PID Controller Tuning
- Heuristic:Huggingface Trl QLoRA BF16 Adapter Casting
- Heuristic:Deepset ai Haystack Document Splitting Defaults
Environments
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Microsoft Agent framework Core Package Dependencies
- Environment:CrewAIInc CrewAI Python Runtime Environment
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:Huggingface Diffusers Quantization Environment
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Langchain ai Langchain OpenAI API Credentials
- Environment:Huggingface Datasets Lance Dependencies
- Environment:Promptfoo Promptfoo Provider API Keys
- Environment:Apache Shardingsphere Java Runtime Environment