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:VainF Torch Pruning CNN Pruning
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:Ggml org Llama cpp Model Perplexity Evaluation
- Workflow:Huggingface Datasets Dataset Streaming
- Workflow:Protectai Llm guard Scanner Benchmarking
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Nightwatchjs Nightwatch Cucumber BDD Integration
- Workflow:Truera Trulens RAG With Guardrails
- Workflow:Online ml River Streaming Anomaly Detection
- Workflow:Puppeteer Puppeteer Browser Installation And Management
Principles
- Principle:PacktPublishing LLM Engineers Handbook Application Configuration Management
- Principle:Ray project Ray Cloud Cluster Provisioning
- Principle:DistrictDataLabs Yellowbrick Type Introspection
- Principle:Eventual Inc Daft Python Package Configuration
- Principle:Diagram of thought Diagram of thought System Prompt Configuration
- Principle:Getgauge Taiko Browser Installation
- Principle:OpenHands OpenHands Business Route Mounting
- Principle:Ggml org Ggml Model Architecture Initialization
- Principle:Webdriverio Webdriverio Documentation Infrastructure
- Principle:Openai Openai python Realtime Conversation Management
Implementations
- Implementation:Junyanz Pytorch CycleGAN and pix2pix Create Dataset
- Implementation:Mlc ai Mlc llm Prepare libs
- Implementation:Ollama Ollama Imagegen MLX C
- Implementation:Avhz RustQuant BarrierOption
- Implementation:Run llama Llama index PairwiseComparisonEvaluator
- Implementation:MarketSquare Robotframework browser Pip Install Browser
- Implementation:Pyro ppl Pyro Pyro Sample
- Implementation:Lance format Lance LqCli
- Implementation:Evidentlyai Evidently Legacy Text Length Feature
- Implementation:Openai Openai python Response Compaction Item
Heuristics
- Heuristic:Bentoml BentoML Adaptive Batching Tuning
- Heuristic:Haosulab ManiSkill Physics Solver Tuning
- Heuristic:Huggingface Peft Warning Deprecated Bone
- Heuristic:Zai org CogVideo LoRA Configuration Tips
- Heuristic:InternLM Lmdeploy KV Quantization Tradeoffs
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
- Heuristic:Googleapis Python genai AFC Max Remote Calls Limit
- Heuristic:Huggingface Datatrove FineWeb Filter Pipeline Order
Environments
- Environment:Hpcaitech ColossalAI CUDA GPU Environment
- Environment:Getgauge Taiko Docker Container
- Environment:Iterative Dvc Remote Storage Backends
- Environment:SeldonIO Seldon core GPU Inference Environment
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Iterative Dvc DVC Environment Variables
- Environment:Mlflow Mlflow Python Runtime Environment
- Environment:Openai Openai python Realtime WebSocket
- Environment:Mbzuai oryx Awesome LLM Post training Python Requests
- Environment:Microsoft Onnxruntime CPU Training Environment