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:Apache Spark Release Process
- Workflow:Apache Beam Twister2 Batch Execution
- Workflow:Sktime Pytorch forecasting DeepAR Probabilistic Forecasting
- Workflow:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Langchain ai Langgraph Building a Stateful Graph
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:TobikoData Sqlmesh Incremental model development
- Workflow:Huggingface Transformers 3D Parallel Distributed Training
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Nightwatchjs Nightwatch Page Object Pattern
Principles
- Principle:Webdriverio Webdriverio BrowserStack Accessibility Testing
- Principle:Helicone Helicone Provider Communication
- Principle:Bitsandbytes foundation Bitsandbytes Mixed Precision Matmul With Outlier Decomposition
- Principle:Hiyouga LLaMA Factory Reward Modeling
- Principle:Ollama Ollama Anthropic API Compatibility
- Principle:PrefectHQ Prefect Global Concurrency Limits
- Principle:Huggingface Optimum Transformation Composition
- Principle:Sdv dev SDV Metadata Detection
- Principle:Scikit learn contrib Imbalanced learn Easy Ensemble
- Principle:DataTalksClub Data engineering zoomcamp Stream Output Sink
Implementations
- Implementation:Alibaba ROLL HomeContent Component
- Implementation:Duckdb Duckdb Mbedtls Cipher
- Implementation:DataExpert io Data engineer handbook Log processing
- Implementation:Ggml org Ggml Cann backend
- Implementation:Deepseek ai Janus LlamaTokenizerFast Decode
- Implementation:Vibrantlabsai Ragas SummarizationScore
- Implementation:Datajuicer Data juicer OptimizeResponseMapper
- Implementation:OWASP Www project top 10 for large language model applications ExploitTracker Analyze
- Implementation:Apache Hudi ClusteringPlanOperator NotifyCheckpointComplete
- Implementation:FMInference FlexLLMGen DeepSpeed Inference Engine
Heuristics
- Heuristic:MarketSquare Robotframework browser Docker Chrome Security
- Heuristic:Predibase Lorax CUDA Graph Batch Size Caching
- Heuristic:Deepset ai Haystack Document Splitting Defaults
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
- Heuristic:Kornia Kornia CPU GPU Branching Tip
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Princeton nlp SimPO Hyperparameter Tuning
- Heuristic:Mbzuai oryx Awesome LLM Post training Depth Limit Recursion At 2
- Heuristic:Run llama Llama index Chunk Size Optimization
- Heuristic:Openai CLIP CLIP Normalization Constants
Environments
- Environment:Eric mitchell Direct preference optimization HuggingFace Transformers
- Environment:Apache Spark Release Build Environment
- Environment:Langchain ai Langgraph Postgres Checkpoint Environment
- Environment:Pola rs Polars GPU Execution Environment
- Environment:Vllm project Vllm CUDA Runtime
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Intel Ipex llm XPU Finetuning Environment
- Environment:Mistralai Client python Azure Deployment Environment
- Environment:OpenRLHF OpenRLHF CUDA GPU Environment
- Environment:Fastai Fastbook Jupyter Notebook Environment