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:Haosulab ManiSkill Custom Task Development
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:OpenBMB UltraFeedback GPT4 Preference Annotation
- Workflow:Microsoft Onnxruntime Python Inference Pipeline
- Workflow:Guardrails ai Guardrails Server Deployment
- Workflow:Ggml org Ggml GPT2 Text Generation
- Workflow:Explodinggradients Ragas Agent Evaluation
- Workflow:Dagster io Dagster Dbt Integration
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:ContextualAI HALOs Model Evaluation
Principles
- Principle:Cleanlab Cleanlab Issue Summarization
- Principle:Huggingface Diffusers ControlNet Architecture
- Principle:Alibaba MNN Output Postprocessing
- Principle:Tensorflow Tfjs Tensor Merging
- Principle:Getgauge Taiko Browser Closure
- Principle:Ggml org Llama cpp Vocabulary System
- Principle:Langgenius Dify Single Node Testing
- Principle:Scikit learn Scikit learn Cross Decomposition
- Principle:ARISE Initiative Robosuite MuJoCo Binding Compatibility
- Principle:Datahub project Datahub Java SDK Dependency Setup
Implementations
- Implementation:Puppeteer Puppeteer NgSchematics Files Util
- Implementation:Apache Flink SplitsRemoval
- Implementation:Pyro ppl Pyro AsymmetricLaplace
- Implementation:Lm sys FastChat Category Label Pipeline
- Implementation:Iterative Dvc To Json
- Implementation:Huggingface Transformers Tests Fetcher
- Implementation:Facebookresearch Habitat lab Rearrange V2 UI Overlay
- Implementation:Mlc ai Mlc llm Attach Support Info
- Implementation:Langchain ai Langgraph Auth Module
- Implementation:ThreeSR Awesome Inference Time Scaling GitHub Fork And Clone
Heuristics
- Heuristic:Dotnet Machinelearning Tokenizer Caching Strategy
- Heuristic:MarketSquare Robotframework browser Windows Shell NPM Workaround
- Heuristic:SeldonIO Seldon core Autoscaling Dual Config Tip
- Heuristic:Langchain ai Langchain Text Splitter Separator Hierarchy
- Heuristic:Fede1024 Rust rdkafka Commit Mode Sync Vs Async
- Heuristic:CarperAI Trlx Delta Rewards
- Heuristic:LLMBook zh LLMBook zh github io Greedy Decoding Temperature Zero
- Heuristic:HKUDS AI Trader Linear Retry Backoff
- Heuristic:Fastai Fastbook Learning Rate Finder Rule
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
Environments
- Environment:Alibaba ROLL Python Runtime Environment
- Environment:AUTOMATIC1111 Stable diffusion webui Xformers Attention
- Environment:CARLA simulator Carla Python API Runtime
- Environment:Bitsandbytes foundation Bitsandbytes ROCm AMD Environment
- Environment:Mit han lab Llm awq CUDA Build Environment
- Environment:Huggingface Alignment handbook DeepSpeed Multi Node
- Environment:Run llama Llama index Fsspec Remote Storage
- Environment:Ray project Ray Python Runtime Environment
- Environment:Sgl project Sglang ROCm
- Environment:Huggingface Optimum Tensor Parallelization Environment