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:ARISE Initiative Robosuite Teleoperation
- Workflow:Shiyu coder Kronos CSV Finetuning
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:CARLA simulator Carla Building from Source
- Workflow:Duckdb Duckdb Source Amalgamation And Packaging
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Openai Openai node Streaming To Client
- Workflow:Langchain ai Langgraph Human in the Loop Agent
- Workflow:Treeverse LakeFS Garbage Collection
- Workflow:Isaac sim IsaacGymEnvs Custom Task Development
Principles
- Principle:Treeverse LakeFS GC Job Execution
- Principle:Avhz RustQuant Generalized Black Scholes Merton
- Principle:Apache Airflow DAG File Discovery
- Principle:Haotian liu LLaVA Visual Instruction Tuning
- Principle:Shiyu coder Kronos Qlib Training Dataset
- Principle:Webdriverio Webdriverio Firefox Profile Management
- Principle:Alibaba ROLL Distillation Validation
- Principle:ARISE Initiative Robomimic Algorithm Instantiation
- Principle:Deepset ai Haystack Query Text Embedding
- Principle:PrefectHQ Prefect Dbt Project Setup
Implementations
- Implementation:Mlc ai Mlc llm Attach Spec Decode Aux
- Implementation:Intel Ipex llm Transformers Trainer LoRA
- Implementation:Datajuicer Data juicer Quality Classifier Train
- Implementation:Bitsandbytes foundation Bitsandbytes XPU Backend Ops
- Implementation:Onnx Onnx Proto Utils
- Implementation:FlowiseAI Flowise PreviewChunks
- Implementation:Alibaba MNN Auto Quant Validation
- Implementation:LaurentMazare Tch rs Tensor Indexing
- Implementation:Langchain ai Langchain BaseChatModel Generate With Cache
- Implementation:CARLA simulator Carla AtomicList
Heuristics
- Heuristic:Alibaba ROLL PPO Clipping Defaults
- Heuristic:InternLM Lmdeploy Max Batch Size Selection
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
- Heuristic:Infiniflow Ragflow Reranking Weight Tuning
- Heuristic:Elevenlabs Elevenlabs python Text Chunking Splitter Characters
- Heuristic:Helicone Helicone Cost Precision Multiplier
- Heuristic:Ucbepic Docetl Optimizer Sample Sizes
- Heuristic:Iamhankai Forest of Thought Tree Iteration Scaling
- Heuristic:Mage ai Mage ai Record Deduplication Before Batch Export
- Heuristic:Apache Kafka Log4j Migration Compatibility
Environments
- Environment:Vespa engine Vespa Cosign Sigstore Signing
- Environment:Cypress io Cypress Node Runtime Environment
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:Alibaba ROLL DeepSpeed Training Environment
- Environment:Openai Whisper PyTorch CUDA
- Environment:PeterL1n BackgroundMattingV2 PyTorch CUDA
- Environment:OWASP Www project top 10 for large language model applications Pre Commit Hooks Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas
- Environment:Huggingface Trl vLLM Generation Environment