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:Zai org CogVideo SAT Finetuning
- Workflow:Evidentlyai Evidently LLM Evaluation Monitoring
- Workflow:Openai Openai node Realtime Conversation
- Workflow:Onnx Onnx Model Creation
- Workflow:CARLA simulator Carla Sensor Data Collection
- Workflow:Apache Kafka Release Candidate Staging
- Workflow:Groq Groq python Audio Transcription
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Langgenius Dify Visual Workflow Builder
- Workflow:VainF Torch Pruning Vision Transformer Pruning
Principles
- Principle:Haifengl Smile File Data Loading
- Principle:Google deepmind Mujoco Plugin Architecture
- Principle:Sgl project Sglang Model Quantization Configuration
- Principle:Microsoft Playwright Set Up Test Resources
- Principle:Deepseek ai Janus Input Tokenization and Batching
- Principle:Ggml org Llama cpp HF to GGUF Conversion
- Principle:Facebookresearch Audiocraft Export Directory Organization
- Principle:Heibaiying BigData Notes Hive Data Loading
- Principle:Openai Openai node Parsed API Invocation
- Principle:Deepspeedai DeepSpeed Accelerator Abstraction
Implementations
- Implementation:Triton inference server Server CommandLineParser
- Implementation:Risingwavelabs Risingwave Handle Create Source
- Implementation:Infiniflow Ragflow UseBulkOperateDataset Hook
- Implementation:CrewAIInc CrewAI OCR Tool
- Implementation:Openai Openai python Tool Types
- Implementation:Open compass VLMEvalKit VLMR1Chat
- Implementation:Alibaba MNN Diffusion Demo CLI
- Implementation:Puppeteer Puppeteer Target
- Implementation:BerriAI Litellm Google GenAI
- Implementation:Groq Groq python Embedding Input Pattern
Heuristics
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
- Heuristic:Apache Flink Async Sink Timeout And Backpressure Defaults
- Heuristic:Huggingface Diffusers Memory Offloading Strategy
- Heuristic:Gretelai Gretel synthetics Batch Size Divisibility Constraints
- Heuristic:Sdv dev SDV Version Compatibility
- Heuristic:Webdriverio Webdriverio Mobile Platform Differences
- Heuristic:Testtimescaling Testtimescaling github io Skip CI Commit Tag
- Heuristic:Volcengine Verl Layered Summon Memory Tradeoff
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Vespa engine Vespa RPM Zstd Compression Settings
Environments
- Environment:Huggingface Optimum Accelerated Inference Environment
- Environment:Openai Openai agents python MCP Dependencies
- Environment:Openclaw Openclaw Mintlify Documentation Platform
- Environment:Speechbrain Speechbrain Multi GPU DDP
- Environment:Googleapis Python genai Python 3 10 SDK Runtime
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:DataTalksClub Data engineering zoomcamp PySpark Batch Environment
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:CarperAI Trlx NeMo Megatron
- Environment:MarketSquare Robotframework browser Node Runtime