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:Huggingface Open r1 GRPO Reasoning Training
- Workflow:Predibase Lorax Server Deployment
- Workflow:NVIDIA NeMo Aligner DPO Training
- Workflow:Duckdb Duckdb Source Amalgamation And Packaging
- Workflow:Ucbepic Docetl YAML Pipeline Execution
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:Confident ai Deepeval End to End LLM Evaluation
- Workflow:Googleapis Python genai Multimodal Content Generation
- Workflow:Apache Paimon Lance Format Analytics
- Workflow:Marker Inc Korea AutoRAG Data Creation Pipeline
Principles
- Principle:Langgenius Dify TanStack Query Integration
- Principle:Mlflow Mlflow Model Version Management
- Principle:Huggingface Diffusers Denoising Loop
- Principle:Ggml org Ggml CANN NPU Computation
- Principle:Online ml River KSWIN Drift Detection
- Principle:Apache Flink Compaction Request Triggering
- Principle:Sdv dev SDV Single Table Quality Evaluation
- Principle:Online ml River Online Ensemble Methods
- Principle:Microsoft Playwright Add Assertions
- Principle:Tencent Ncnn C Language Binding
Implementations
- Implementation:Openai Openai agents python ApplyPatchTool Pattern
- Implementation:SqueezeAILab ETS Evaluate And Majority Vote
- Implementation:Confident ai Deepeval Changelog Generator
- Implementation:Datajuicer Data juicer MaximumLineLengthFilter
- Implementation:Hpcaitech ColossalAI AGIEvalDataset
- Implementation:Huggingface Optimum Run And TimeBenchmark
- Implementation:LaurentMazare Tch rs Precompute Freqs Cis
- Implementation:Webdriverio Webdriverio XPath Converter
- Implementation:SeleniumHQ Selenium Python Pyproject
- Implementation:BerriAI Litellm MCP Client
Heuristics
- Heuristic:SeldonIO Seldon core Over Commit Memory Tip
- Heuristic:TA Lib Ta lib python STOCHRSI Vs STOCH RSI
- Heuristic:Predibase Lorax GPU Sampling Optimization
- Heuristic:Confident ai Deepeval Async Concurrency Tuning
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:Openai CLIP FP16 FP32 Dtype Handling
- Heuristic:Wandb Weave Sentinel Value Handling
- Heuristic:Google research Deduplicate text datasets HACKSIZE Overlap Buffer
- Heuristic:Speechbrain Speechbrain Separation Loss Filtering
- Heuristic:Arize ai Phoenix Warning Deprecated VertexAIModel
Environments
- Environment:Elevenlabs Elevenlabs python Python Httpx
- Environment:Alibaba ROLL DeepSpeed Training Environment
- Environment:Langchain ai Langchain LangSmith Tracing Config
- Environment:Apache Hudi Flink Runtime Environment
- Environment:Online ml River Build Toolchain
- Environment:Helicone Helicone Node 20 TypeScript Runtime
- Environment:SeldonIO Seldon core Docker Compose Local Environment
- Environment:Princeton nlp SimPO CUDA Training
- Environment:Duckdb Duckdb Release Publishing Env
- Environment:Huggingface Open r1 CUDA Environment