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:Vibrantlabsai Ragas Agent Evaluation
- Workflow:Spotify Luigi Local Batch Pipeline
- Workflow:Anthropics Anthropic sdk python Structured Output Extraction
- Workflow:Apache Airflow Core Release Process
- Workflow:Protectai Modelscan Programmatic Model Scanning
- Workflow:Haosulab ManiSkill RL Training with PPO
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
- Workflow:Microsoft Playwright Browser automation CLI
Principles
- Principle:Pytorch Serve Streaming Cloud Inference
- Principle:Volcengine Verl SAPO Algorithm
- Principle:Mlflow Mlflow Code Instrumentation
- Principle:Obss Sahi COCO Dataset Loading
- Principle:Getgauge Taiko REPL Initialization
- Principle:Langchain ai Langgraph Type System
- Principle:Apache Kafka Coordinator Read Operations
- Principle:Ggml org Ggml CPU Tensor Operations
- Principle:Nautechsystems Nautilus trader Data Event Handling
- Principle:Kornia Kornia Grayscale Conversion
Implementations
- Implementation:Dagster io Dagster ML Pipeline Assets
- Implementation:Protectai Llm guard Output BanSubstrings
- Implementation:Datahub project Datahub KafkaEmitter
- Implementation:Run llama Llama index Settings Embed Model Assignment
- Implementation:NVIDIA DALI NumPy Header
- Implementation:Alibaba ROLL McaTrainer
- Implementation:Ggml org Llama cpp Memory Recurrent Header
- Implementation:Alibaba MNN OpenCL CL Ext Intel Header
- Implementation:Kubeflow Pipelines Helm Pipeline Template
- Implementation:Online ml River Metrics SMAPE
Heuristics
- Heuristic:Explodinggradients Ragas Embedding Batch Size Tuning
- Heuristic:NVIDIA DALI Batch Size Tuning
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Diagram of thought Diagram of thought Strict Vs Flexible Critic Rigor
- Heuristic:TA Lib Ta lib python STOCHRSI Vs STOCH RSI
- Heuristic:FlagOpen FlagEmbedding Dynamic Batch Size Reduction
- Heuristic:FlagOpen FlagEmbedding Gradient Checkpointing Tip
- Heuristic:Microsoft DeepSpeedExamples RLHF Stability Constraints
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:Volcengine Verl Layered Summon Memory Tradeoff
Environments
- Environment:Diagram of thought Diagram of thought LLM API
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Openai Openai node OpenAI API Credentials
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Cohere ai Cohere python Cohere API Credentials
- Environment:Deepspeedai DeepSpeed CPU Environment
- Environment:SeldonIO Seldon core Python ML Dependencies Environment
- Environment:OWASP Www project top 10 for large language model applications Pre Commit Hooks Environment
- Environment:Arize ai Phoenix Python Runtime