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:Volcengine Verl Multi Turn Tool Use Training
- Workflow:Google deepmind Dm control MJCF Model Composition
- Workflow:Infiniflow Ragflow Docker Deployment
- Workflow:Dagster io Dagster Modal Serverless Pipeline
- Workflow:Mit han lab Llm awq AWQ Model Quantization
- Workflow:Tensorflow Serving Batched Inference Pipeline
- Workflow:Lucidrains X transformers DPO Preference Alignment
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:Ucbepic Docetl Python API Pipeline
- Workflow:TobikoData Sqlmesh Model development and testing
Principles
- Principle:Kserve Kserve Data Transformation
- Principle:Ggml org Llama cpp Speculation Strategy Selection
- Principle:Zai org CogVideo VAE Encode Decode
- Principle:Huggingface Diffusers Lazy Import Management
- Principle:Pyro ppl Pyro JIT Compilation
- Principle:Openai Openai agents python Streamed Run Invocation
- Principle:Datahub project Datahub Pipeline Execution
- Principle:Mlc ai Mlc llm Model Packaging Configuration
- Principle:Google deepmind Mujoco Model Compilation
- Principle:Obss Sahi Project Configuration
Implementations
- Implementation:Deepset ai Haystack Logging Configuration
- Implementation:AUTOMATIC1111 Stable diffusion webui Restore faces
- Implementation:Tencent Ncnn MobileNetV3 SSDLite Example
- Implementation:Microsoft Onnxruntime TensorInfo
- Implementation:Scikit learn Scikit learn RankingMetrics
- Implementation:Alibaba ROLL Merge LoRA Into State Dict
- Implementation:Tensorflow Tfjs Backend Operations Test
- Implementation:Pyro ppl Pyro Importance
- Implementation:Apache Dolphinscheduler NettyRemotingServer Setup
- Implementation:Nightwatchjs Nightwatch Cucumber Runner Config
Heuristics
- Heuristic:Spcl Graph of thoughts Backoff Retry On API Errors
- Heuristic:Tensorflow Serving Resource Estimation Rules
- Heuristic:Interpretml Interpret Memory Budget Heuristic
- Heuristic:Webdriverio Webdriverio Stale Element Auto Refetch
- Heuristic:Truera Trulens Feedback Score Thresholds
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:Microsoft Agent framework Function Invocation Defaults
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:Apache Shardingsphere Version Cleanup After Switch
- Heuristic:Dotnet Machinelearning Text File Sampling Strategy
Environments
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:Openai Openai python Voice Helpers
- Environment:Gretelai Gretel synthetics PyTorch CUDA Environment
- Environment:Alibaba ROLL Python Runtime Environment
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:Mlc ai Mlc llm CUDA GPU Environment
- Environment:Langgenius Dify Node Frontend Environment