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:Neuml Txtai API Deployment
- Workflow:Ollama Ollama OpenAI API Compatibility
- Workflow:Openai Openai agents python Basic Agent Execution
- Workflow:Volcengine Verl Data Preprocessing For RL
- Workflow:FlagOpen FlagEmbedding Embedder Inference
- Workflow:AUTOMATIC1111 Stable diffusion webui Image postprocessing and upscaling
- Workflow:Apache Dolphinscheduler RPC Service Communication
- Workflow:Bigscience workshop Petals Distributed Text Generation
- Workflow:Bitsandbytes foundation Bitsandbytes 8bit Optimizer Training
- Workflow:Trailofbits Fickling Pickle Safety Analysis
Principles
- Principle:CARLA simulator Carla Source Repository Setup
- Principle:FMInference FlexLLMGen Model Configuration Resolution
- Principle:Tensorflow Serving Dependency Ownership
- Principle:LaurentMazare Tch rs Custom Dataset Loading
- Principle:DataTalksClub Data engineering zoomcamp Parquet Output Writing
- Principle:Protectai Llm guard Token Limit Enforcement
- Principle:Apache Dolphinscheduler RPC Client Proxy Pattern
- Principle:Mlc ai Web llm Extension Service Worker
- Principle:Allenai Open instruct GRPO Checkpointing
- Principle:Allenai Open instruct DPO Training
Implementations
- Implementation:Testtimescaling Testtimescaling github io Paper Taxonomy Analysis
- Implementation:Eventual Inc Daft Daft Func Batch
- Implementation:Googleapis Python genai Operations Converters
- Implementation:Online ml River Tree Nodes HTC
- Implementation:Datajuicer Data juicer NaiveGrouper
- Implementation:Run llama Llama index Adapter Training Utils
- Implementation:Ollama Ollama Convert Qwen3Vl
- Implementation:Dotnet Machinelearning ForecastBySsa
- Implementation:Helicone Helicone Providers Index
- Implementation:Scikit learn Scikit learn ArrayAPI
Heuristics
- Heuristic:Kornia Kornia CPU GPU Branching Tip
- Heuristic:InternLM Lmdeploy KV Cache Memory Tuning
- Heuristic:Openai Whisper Compression Ratio Threshold
- Heuristic:Axolotl ai cloud Axolotl Memory Optimization Tips
- Heuristic:Apache Airflow DAG Top Level Code Avoidance
- Heuristic:HKUDS AI Trader DeepSeek Tool Args Workaround
- Heuristic:Diagram of thought Diagram of thought Typed Records For Auditability
- Heuristic:OpenBMB UltraFeedback GPU Memory Utilization
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:OpenGVLab InternVL LoRA Alpha Scaling
Environments
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Sgl project Sglang Performance Dashboard
- Environment:Googleapis Python genai Gemini API Key Authentication
- Environment:Scikit learn contrib Imbalanced learn Keras TensorFlow
- Environment:Huggingface Peft BitsAndBytes Quantization
- Environment:Allenai Open instruct Ray Distributed
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Microsoft BIPIA OpenAI API Environment