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:Ray project Ray Remote Task Execution
- Workflow:Shiyu coder Kronos Batch Prediction
- Workflow:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:Shiyu coder Kronos Single Series Prediction
- Workflow:Microsoft Onnxruntime Train Convert Predict
- Workflow:NVIDIA NeMo Aligner REINFORCE Training
- Workflow:Promptfoo Promptfoo CI CD Integration
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Lm sys FastChat MT Bench Evaluation
- Workflow:InternLM Lmdeploy W4A16 AWQ Quantization
Principles
- Principle:TobikoData Sqlmesh CICD Bot Configuration
- Principle:Neuml Txtai Index Construction
- Principle:OWASP Www project top 10 for large language model applications Entry Refinement and Revoting
- Principle:Ggml org Llama cpp Model Management
- Principle:Haotian liu LLaVA Conversation Prompt Construction
- Principle:AUTOMATIC1111 Stable diffusion webui Launch Sequence
- Principle:Kubeflow Pipelines Parquet Model Training
- Principle:LaurentMazare Tch rs GPT Text Generation
- Principle:Tencent Ncnn Python Bindings Build
- Principle:Nightwatchjs Nightwatch BDD Style Expect Assertions
Implementations
- Implementation:Openai Openai python Response Refusal Done
- Implementation:Open compass VLMEvalKit EMMADataset
- Implementation:Pytorch Serve Transformer Handler Config
- Implementation:NVIDIA DALI EfficientDet Dataloader
- Implementation:Microsoft Playwright Public API Types
- Implementation:CrewAIInc CrewAI Enterprise API Spec Ko
- Implementation:Apache Druid Json Completion Engine
- Implementation:Run llama Llama index SQLDatabase
- Implementation:Spotify Luigi SparkSubmitTask Config
- Implementation:Onnx Onnx Model Subgraph Extractor
Heuristics
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Datahub project Datahub Gradle Formatting Over Direct Tools
- Heuristic:Huggingface Datasets Batch Size Optimization
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:Alibaba ROLL Reward Clipping Normalization
- Heuristic:Openai Openai agents python Sensitive Data Logging Defaults
- Heuristic:NVIDIA NeMo Curator Video Frame Sampling Strategy
- Heuristic:Huggingface Transformers Label Smoothing Multi Label Warning
- Heuristic:Openai Openai node Retry Backoff Configuration
- Heuristic:Lm sys FastChat GPU Memory Allocation Strategy
Environments
- Environment:Openai Whisper Numba
- Environment:Guardrails ai Guardrails LLM Provider API Keys
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment
- Environment:Google deepmind Mujoco C Build Environment
- Environment:Treeverse LakeFS Go Runtime Environment
- Environment:Shiyu coder Kronos HuggingFace Hub Access
- Environment:Apache Spark Python Environment
- Environment:Apache Shardingsphere ZooKeeper Cluster Coordination
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Recommenders team Recommenders GPU CUDA Environment