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 Robomimic Trained Policy Evaluation
- Workflow:Openai Openai agents python Basic Agent Execution
- Workflow:Puppeteer Puppeteer Page Screenshot Capture
- Workflow:Speechbrain Speechbrain Speech Separation Training
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:Sdv dev SDV Constrained synthesis
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:Google deepmind Dm control Control Suite RL Training
- Workflow:DataExpert io Data engineer handbook PySpark Job Testing
Principles
- Principle:Vllm project Vllm Multimodal Prompt Formatting
- Principle:Dagster io Dagster Incremental Processing
- Principle:Nautechsystems Nautilus trader Python Package Configuration
- Principle:Langgenius Dify DataTransformation
- Principle:Microsoft LoRA NLG Dataset Preparation
- Principle:Webdriverio Webdriverio Session Management
- Principle:Evidentlyai Evidently Project Configuration
- Principle:Openai Openai python Fine Tuning Job Monitoring
- Principle:Ggml org Llama cpp Speculative Decoding
- Principle:Langgenius Dify App Type Selection
Implementations
- Implementation:Avhz RustQuant Graph and Variable
- Implementation:Huggingface Diffusers LoRA Training Config
- Implementation:Spotify Luigi SalesforceAPI
- Implementation:Iterative Dvc Database
- Implementation:Kornia Kornia Pyproject Config
- Implementation:Online ml River Stats Mode
- Implementation:Ollama Ollama VerifyBlob
- Implementation:BerriAI Litellm Batch Utils
- Implementation:ARISE Initiative Robosuite TableArena
- Implementation:Huggingface Transformers Models To Deprecate
Heuristics
- Heuristic:MarketSquare Robotframework browser Shared Node Process For Parallel
- Heuristic:Cohere ai Cohere python Warning Deprecated Legacy Generate API
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:Mlc ai Web llm Multi Round KV Cache Reuse
- Heuristic:Alibaba ROLL Dynamic Batching Token Limits
- Heuristic:Protectai Modelscan Unknown Opcodes Assume Critical
- Heuristic:Shiyu coder Kronos Two Stage Finetuning Strategy
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Spcl Graph of thoughts Budget Gated Benchmark Execution
Environments
- Environment:Princeton nlp Tree of thought llm Python OpenAI
- Environment:Neuml Txtai Docker Deployment Environment
- Environment:Mlc ai Mlc llm Python Serving Environment
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Langgenius Dify Credentials And Env Vars
- Environment:Liu00222 Open Prompt Injection CUDA Environment
- Environment:Danijar Dreamerv3 JAX CUDA
- Environment:Eventual Inc Daft Ray Distributed Runner
- Environment:Obss Sahi Python Pycocotools
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment