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:Promptfoo Promptfoo Custom Provider Integration
- Workflow:Openai Openai python Fine Tuning Job Management
- Workflow:Kubeflow Pipelines XGBoost Training Pipeline
- Workflow:Haotian liu LLaVA LoRA Finetuning
- Workflow:Openai Whisper Word Level Timestamps
- Workflow:Ollama Ollama Model Registry Operations
- Workflow:Neuml Txtai Model Training
- Workflow:Mistralai Client python GCP Chat Completion
- Workflow:OpenGVLab InternVL Multi Stage Pretraining
- Workflow:Ggml org Llama cpp HF to GGUF Model Conversion
Principles
- Principle:Confident ai Deepeval Test Case Construction
- Principle:Deepseek ai Janus Conversation Formatting
- Principle:NVIDIA NeMo Curator Video Ingestion
- Principle:Hiyouga LLaMA Factory Dataset Format Conversion
- Principle:Haosulab ManiSkill Robot Agent Definition
- Principle:Apache Paimon Blob Descriptor Construction
- Principle:PacktPublishing LLM Engineers Handbook Supervised Finetuning
- Principle:Microsoft Playwright Configure Recording Context
- Principle:Lucidrains X transformers GPT Variational Autoencoder
- Principle:Microsoft Playwright Inject Browser API Mocks
Implementations
- Implementation:Ollama Ollama Llama Json Schema To Grammar
- Implementation:CrewAIInc CrewAI Databricks Query Tool
- Implementation:Ggml org Ggml Sam image preprocess
- Implementation:Facebookresearch Audiocraft RotaryEmbedding
- Implementation:Apache Flink SplitReader
- Implementation:Microsoft Autogen Studio Generate Image Tool
- Implementation:CARLA simulator Carla Client Set Replayer Time Factor
- Implementation:Ggml org Llama cpp Preset Header
- Implementation:ClickHouse ClickHouse SSLManager InitializeServer
- Implementation:Open compass VLMEvalKit Check Command
Heuristics
- Heuristic:Scikit learn Scikit learn Working Memory Tuning
- Heuristic:Allenai Open instruct Polyak Reference Update
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:OpenHands OpenHands Fail Open Rate Limiting
- Heuristic:Isaac sim IsaacGymEnvs Factory Velocity Limits
- Heuristic:NVIDIA NeMo Aligner Higher Stability Log Probs
- Heuristic:Microsoft Onnxruntime ORTModule Wrapping Order
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:Avhz RustQuant MC Parallel Path Threshold
- Heuristic:Apache Druid Auto Granularity Selection
Environments
- Environment:PeterL1n BackgroundMattingV2 PyTorch CUDA
- Environment:Langgenius Dify Vector Database Environment
- Environment:Alibaba ROLL Diffusion Video Environment
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:DistrictDataLabs Yellowbrick Python Scikit Learn Environment
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Protectai Modelscan TensorFlow Optional
- Environment:Huggingface Datasets Audio Video Dependencies
- Environment:Apache Paimon Python Core Runtime