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 Agent framework Agent With Tool Approval
- Workflow:Hiyouga LLaMA Factory PPO RLHF Training
- Workflow:Protectai Modelscan Programmatic Model Scanning
- Workflow:Volcengine Verl GRPO Training Pipeline
- Workflow:MarketSquare Robotframework browser Installation and Setup
- Workflow:Unslothai Unsloth Vision Model Finetuning
- Workflow:Huggingface Peft LoRA Embedding Semantic Search
- Workflow:Huggingface Transformers Model Training With Trainer
- Workflow:Onnx Onnx Version Conversion
- Workflow:Arize ai Phoenix Dataset and Experiment Lifecycle
Principles
- Principle:Mistralai Client python Stream Lifecycle Management
- Principle:Guardrails ai Guardrails Hub Submission
- Principle:Google deepmind Mujoco PGS Solver
- Principle:Google deepmind Mujoco Scene Rendering
- Principle:Huggingface Transformers Model Evaluation
- Principle:MarketSquare Robotframework browser Library Import and Configuration
- Principle:EvolvingLMMs Lab Lmms eval Data Tooling
- Principle:Bigscience workshop Petals Chatbot Model Loading
- Principle:Ggml org Ggml Python Tensor Interop
- Principle:Vllm project Vllm Multimodal Output Processing
Implementations
- Implementation:Unslothai Unsloth Llama4 MoE Block
- Implementation:Microsoft Autogen Studio Component Editor
- Implementation:Promptfoo Promptfoo CSV Parser
- Implementation:Allenai Open instruct SFTDatasetProcessor
- Implementation:Hiyouga LLaMA Factory Pairwise Processor
- Implementation:Online ml River Tree MondrianTreeNodes
- Implementation:Open compass VLMEvalKit TaichuVLWrapper
- Implementation:Infiniflow Ragflow TagWordCloud Component
- Implementation:Huggingface Trl AutoModelForCausalLM From Pretrained DPO
- Implementation:Hpcaitech ColossalAI SafetyBenchZHDataset
Heuristics
- Heuristic:Apache Flink Bin Packing Complexity Guard
- Heuristic:OpenHands OpenHands Fail Open Rate Limiting
- Heuristic:Google research Deduplicate text datasets Variable Width Pointer Optimization
- Heuristic:ThreeSR Awesome Inference Time Scaling Empty Venue Default Tip
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:Arize ai Phoenix Environment Variable Precedence
- Heuristic:Cleanlab Cleanlab Label Quality Scoring Method Selection
- Heuristic:Promptfoo Promptfoo WAL Mode Network Filesystem
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Apache Druid Auto Granularity Selection
Environments
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:Openclaw Openclaw Docker Deployment Environment
- Environment:Haotian liu LLaVA Python CUDA Training Environment
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Vllm project Vllm NVIDIA CUDA
- Environment:CarperAI Trlx Python Accelerate
- Environment:Mlc ai Mlc llm WebGPU Browser Environment
- Environment:Eventual Inc Daft Python PyArrow Core
- Environment:Volcengine Verl vLLM Rollout Environment
- Environment:Cohere ai Cohere python Python SDK Runtime