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:DistrictDataLabs Yellowbrick Model Selection and Tuning
- Workflow:Snorkel team Snorkel Multitask Classification
- Workflow:LaurentMazare Tch rs Transfer Learning
- Workflow:Deepset ai Haystack Document Indexing Pipeline
- Workflow:Norrrrrrr lyn WAInjectBench Image Prompt Injection Detection
- Workflow:NVIDIA NeMo Curator Fuzzy Deduplication
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:NVIDIA NeMo Aligner Supervised Fine Tuning
- Workflow:Ollama Ollama Custom Model Creation
- Workflow:Anthropics Anthropic sdk python Extended Thinking Reasoning
Principles
- Principle:ClickHouse ClickHouse Overflow Safe Arithmetic
- Principle:ClickHouse ClickHouse BFloat16 Type
- Principle:Huggingface Optimum Parameter Metadata Initialization
- Principle:LLMBook zh LLMBook zh github io ALiBi Position Encoding
- Principle:AnswerDotAI RAGatouille In Memory Search
- Principle:Lucidrains X transformers Continuous Sequence Modeling
- Principle:Puppeteer Puppeteer Data Extraction
- Principle:Risingwavelabs Risingwave Streaming Source Ingestion
- Principle:FlowiseAI Flowise Workspace Management
- Principle:Googleapis Python genai Cache Management
Implementations
- Implementation:Langgenius Dify Feature Types
- Implementation:Ollama Ollama Anthropic Handler
- Implementation:Getgauge Taiko LinkWrapper
- Implementation:Microsoft Onnxruntime Numpy Output Extraction
- Implementation:Ucbepic Docetl MOAR SearchUtils
- Implementation:Promptfoo Promptfoo resolveConfigs
- Implementation:LMCache LMCache L1 Manager
- Implementation:Google deepmind Dm control Soccer Observables
- Implementation:TobikoData Sqlmesh TasksOverview
- Implementation:Tencent Ncnn SimpleOCV
Heuristics
- Heuristic:Pytorch Serve CPU Performance Tuning
- Heuristic:Togethercomputer Together python Retry Backoff Strategy
- Heuristic:Trailofbits Fickling Race Condition Prevention
- Heuristic:SeleniumHQ Selenium Cross Binding Consistency Check
- Heuristic:Langgenius Dify Workflow Draft Hash Sync
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:Neuml Txtai Model Quantization Defaults
- Heuristic:Bitsandbytes foundation Bitsandbytes Compressed Statistics Double Quantization
- Heuristic:Apache Dolphinscheduler Load Balancer Strategy Selection
- Heuristic:Fastai Fastbook Batch Size Selection
Environments
- Environment:Protectai Llm guard API Server Deployment
- Environment:Openai Openai agents python Python 3 9 Runtime
- Environment:Apache Shardingsphere Java Runtime Environment
- Environment:Scikit learn Scikit learn Python Runtime Environment
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Microsoft Autogen Python Runtime Environment
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:Kubeflow Pipelines KFP Backend Deployment
- Environment:Vespa engine Vespa POSIX Mmap Log Control
- Environment:Haosulab ManiSkill Real Robot LeRobot Deps