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:BerriAI Litellm SDK Completion
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:Cleanlab Cleanlab Object Detection Label Quality
- Workflow:Lucidrains X transformers Non Autoregressive Masked Generation
- Workflow:Groq Groq python Text Embedding
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:ContextualAI HALOs Offline SFT Alignment Pipeline
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Microsoft Onnxruntime Train Convert Predict
- Workflow:Google deepmind Dm control Control Suite RL Training
Principles
- Principle:Fede1024 Rust rdkafka Transactional Message Production
- Principle:Roboflow Rf detr Finetuned Model Loading
- Principle:CrewAIInc CrewAI Semantic Retrieval
- Principle:HKUDS AI Trader A Share Data Fetching
- Principle:CarperAI Trlx Offline RL Training
- Principle:Online ml River Online Nearest Neighbors
- Principle:Langchain ai Langchain Structured Output Extraction
- Principle:ClickHouse ClickHouse Pull Request Submission
- Principle:Risingwavelabs Risingwave CDC PostgreSQL Schema Management
- Principle:Langgenius Dify Role Based Access Control
Implementations
- Implementation:Lance format Lance PrimitiveBlobDecoding
- Implementation:NVIDIA TransformerEngine ONNX Export
- Implementation:DevExpress Testcafe ScreenshotCapturer
- Implementation:Datahub project Datahub Pipeline Create And Run
- Implementation:Neuml Txtai ImageHash
- Implementation:Ggml org Ggml Cpu spacemit ime1 kernels
- Implementation:Mlflow Mlflow Pyfunc Load Model
- Implementation:ClickHouse ClickHouse Nfpm Server Package
- Implementation:Facebookresearch Habitat lab HumanoidSeqPoseController
- Implementation:NVIDIA TransformerEngine TE LayerNormLinear
Heuristics
- Heuristic:LLMBook zh LLMBook zh github io BF16 Mixed Precision Default
- Heuristic:Lance format Lance Warning Deprecated Java APIs
- Heuristic:Risingwavelabs Risingwave Source Backoff Strategy
- Heuristic:Mage ai Mage ai Batch Size Tuning
- Heuristic:Tensorflow Tfjs WASM Cross Origin Isolation
- Heuristic:EvolvingLMMs Lab Lmms eval Truncated Image Handling
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Mlfoundations Open flamingo Gradient Clipping Max Norm
- Heuristic:ChenghaoMou Text dedup Mersenne Prime Backward Compatibility
Environments
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Neuml Txtai API Server Configuration
- Environment:Infiniflow Ragflow GPU CUDA Environment
- Environment:Apache Beam Portable Runner Environment
- Environment:DataExpert io Data engineer handbook PostgreSQL Docker Environment
- Environment:Vllm project Vllm CUDA Hopper
- Environment:Microsoft Semantic kernel DotNet SDK Environment
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:Langgenius Dify Python Backend Environment