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:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:Open compass VLMEvalKit Video Benchmark Evaluation
- Workflow:Pytorch Serve LLM Deployment vLLM
- Workflow:ClickHouse ClickHouse Contributing Pull Request
- Workflow:MarketSquare Robotframework browser Library Development and Release
- Workflow:Microsoft Onnxruntime On Device Training
- Workflow:Bigscience workshop Petals Prompt Tuning Chatbot
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Tensorflow Tfjs GPT2 Text Generation
- Workflow:Sgl project Sglang Offline Batch Inference
Principles
- Principle:Vespa engine Vespa Logger Handler Installation
- Principle:Neuml Txtai RAG Index Building
- Principle:InternLM Lmdeploy Engine Configuration
- Principle:Evidentlyai Evidently Snapshot Export
- Principle:Elevenlabs Elevenlabs python Audio Interface
- Principle:Isaac sim IsaacGymEnvs Task Selection and Configuration
- Principle:Huggingface Diffusers LoRA Export
- Principle:Apache Paimon Batch Data Writing
- Principle:Zai org CogVideo Video Export
- Principle:Huggingface Transformers Distributed Checkpointing
Implementations
- Implementation:Langgenius Dify UseModerate
- Implementation:Haosulab ManiSkill HumanoidPickPlace
- Implementation:Alibaba MNN FlatBuffers IDL Gen gRPC
- Implementation:Explodinggradients Ragas LocalJSONLBackend Class
- Implementation:Facebookresearch Audiocraft GeneralUtils
- Implementation:Kserve Kserve LLM Prefill Worker DP Config
- Implementation:Zai org CogVideo SSIM MS SSIM
- Implementation:SeleniumHQ Selenium PageLoadStrategy
- Implementation:Avhz RustQuant LookbackOption
- Implementation:SeleniumHQ Selenium ExecutableFinder
Heuristics
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
- Heuristic:Mlc ai Mlc llm Metal KV Cache Capacity Limit
- Heuristic:BerriAI Litellm Streaming Loop Detection
- Heuristic:Duckdb Duckdb Memory Management Rules
- Heuristic:Norrrrrrr lyn WAInjectBench Union Ensemble Maximize Recall
- Heuristic:Sail sg LongSpec NCCL Distributed Settings
- Heuristic:Microsoft Semantic kernel Prompt Injection Safety
- Heuristic:Sdv dev SDV Gaussian KDE Incompatibility
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:Fastai Fastbook Mixup Data Augmentation
Environments
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:MaterializeInc Materialize Kubernetes Helm Runtime
- Environment:Testtimescaling Testtimescaling github io Python 3 Runtime
- Environment:Huggingface Diffusers Attention Backends
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Vllm project Vllm CUDA Hopper
- Environment:Ucbepic Docetl Python Runtime
- Environment:Pola rs Polars Cloud Storage Environment