Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Microsoft Playwright Codegen test recording
- Workflow:Mistralai Client python Function Calling
- Workflow:Hiyouga LLaMA Factory Model Inference and Serving
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:Wandb Weave Tracing Setup
- Workflow:Ggml org Ggml GPT2 Text Generation
- Workflow:Huggingface Alignment handbook QLoRA Single GPU Finetuning
- Workflow:Protectai Llm guard PII Anonymization Deanonymization
- Workflow:Alibaba MNN LLM Deployment Pipeline
- Workflow:Openai Evals Running a single eval
Principles
- Principle:Hpcaitech ColossalAI Retrieval Augmented QA
- Principle:OpenGVLab InternVL Flash Attention Optimization
- Principle:FlagOpen FlagEmbedding Multi Retrieval Training
- Principle:Spcl Graph of thoughts Graph Reasoning Execution
- Principle:Neuml Txtai ONNX Export
- Principle:Norrrrrrr lyn WAInjectBench Per Folder Image Detection
- Principle:Nightwatchjs Nightwatch Component Environment Configuration
- Principle:Ggml org Llama cpp GGUFFormat
- Principle:Facebookresearch Habitat lab Registry Registration
- Principle:Hpcaitech ColossalAI GRPO Reward Configuration
Implementations
- Implementation:Togethercomputer Together python Speech Create
- Implementation:Spotify Luigi PrometheusMetricsCollector
- Implementation:Anthropics Anthropic sdk python Messages Create
- Implementation:FlowiseAI Flowise Table
- Implementation:Apache Druid PortalBubble
- Implementation:Getgauge Taiko Element Base
- Implementation:Webdriverio Webdriverio Remote Function
- Implementation:Langchain ai Langchain XAI Model Profiles
- Implementation:LMCache LMCache KVController
- Implementation:Huggingface Optimum GPTQ Fasterquant
Heuristics
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:ARISE Initiative Robomimic Data Worker Tuning By Modality
- Heuristic:Vllm project Vllm Batch Size Hardware Scaling
- Heuristic:HKUDS AI Trader A Share Lot Size Rule
- Heuristic:Spotify Luigi PySpark Task Serialization
- Heuristic:AnswerDotAI RAGatouille Auto Batch Size For Long Documents
- Heuristic:Kubeflow Kubeflow Stale Issue Lifecycle Management
- Heuristic:Unstructured IO Unstructured Strategy Fallback Chain
- Heuristic:Huggingface Optimum Version Conditional Behavior
- Heuristic:Obss Sahi Auto Slice Resolution
Environments
- Environment:Nautechsystems Nautilus trader Arrow Parquet Serialization
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:Snorkel team Snorkel SpaCy NLP
- Environment:Evidentlyai Evidently Grafana Monitoring Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:Deepspeedai DeepSpeed Python Runtime Environment
- Environment:Spotify Luigi Python Runtime