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:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:ARISE Initiative Robomimic Trained Policy Evaluation
- Workflow:Cypress io Cypress CI Pipeline Integration
- Workflow:Google research Deduplicate text datasets Single file deduplication
- Workflow:Huggingface Diffusers Model Quantization
- Workflow:Promptfoo Promptfoo CI CD Integration
- Workflow:LMCache LMCache CacheBlend KV Reuse
- Workflow:DevExpress Testcafe CI Integration
- Workflow:Langgenius Dify Plugin Management
- Workflow:Evidentlyai Evidently LLM Evaluation Monitoring
Principles
- Principle:Kserve Kserve InferenceGraph Specification
- Principle:Sgl project Sglang Server Arguments Configuration
- Principle:Princeton nlp Tree of thought llm Usage Tracking
- Principle:Apache Airflow Operator Sensor Development
- Principle:Marker Inc Korea AutoRAG Pipeline Query Execution
- Principle:Haotian liu LLaVA Result Format Conversion
- Principle:Iterative Dvc Dependency Graph Validation
- Principle:Onnx Onnx External Data Conversion
- Principle:Pytorch Serve Server Lifecycle
- Principle:SeldonIO Seldon core Explainer Readiness Verification
Implementations
- Implementation:Datajuicer Data juicer VideoTaggingFromFramesMapper
- Implementation:Ggml org Ggml Cpu s390 quants
- Implementation:Iterative Dvc Utils Collections
- Implementation:Onnx Onnx Load External Data For Model
- Implementation:Cypress io Cypress CreateInstance
- Implementation:Risingwavelabs Risingwave OpensearchBulkProcessorAdapter
- Implementation:Turboderp org Exllamav2 Attn Params
- Implementation:Treeverse LakeFS UploadObject For Actions
- Implementation:Teamcapybara Capybara CSSBuilder
- Implementation:Open compass VLMEvalKit VILA
Heuristics
- Heuristic:Cohere ai Cohere python Pydantic V1 V2 Compatibility
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:Fastai Fastbook Weight Decay Tuning
- Heuristic:TobikoData Sqlmesh Forward Only Safety
- Heuristic:Tencent Ncnn FP16 Precision Selection
- Heuristic:SeldonIO Seldon core Tracing Latency Tip
- Heuristic:Google deepmind Dm control Prop Settling Physics Tuning
- Heuristic:Puppeteer Puppeteer Mac Silicon Performance
- Heuristic:AnswerDotAI RAGatouille Searcher Configuration By Collection Size
- Heuristic:Shiyu coder Kronos Learning Rate And Optimizer Tuning
Environments
- Environment:Google deepmind Mujoco Python Bindings Environment
- Environment:DataTalksClub Data engineering zoomcamp Dbt DuckDB Environment
- Environment:Langfuse Langfuse Node 24 Runtime
- Environment:Vllm project Vllm ROCm
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:TobikoData Sqlmesh Dbt Compatibility
- Environment:Neuml Txtai GPU Accelerator Detection
- Environment:Ggml org Llama cpp CMake Build Environment
- Environment:Openai Openai python Realtime WebSocket
- Environment:Iamhankai Forest of Thought OpenAI API Credentials