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:Facebookresearch Habitat lab Custom Task Extension
- Workflow:Dagster io Dagster Dbt Integration
- Workflow:Promptfoo Promptfoo LLM Evaluation
- Workflow:Mistralai Client python OCR Document Processing
- Workflow:Haifengl Smile Nearest Neighbor Search
- Workflow:Sktime Pytorch forecasting DeepAR Probabilistic Forecasting
- Workflow:Protectai Llm guard API Server Deployment
- Workflow:Dagster io Dagster ML Pipeline
- Workflow:Apache Druid Streaming Ingestion Management
- Workflow:Huggingface Optimum FX Graph Optimization
Principles
- Principle:Mlc ai Mlc llm Mobile Build Environment
- Principle:Spcl Graph of thoughts Document Merging Prompt Design
- Principle:Openai Openai python Input Token Counting
- Principle:OpenGVLab InternVL Component Model Assembly
- Principle:Scikit learn Scikit learn Parameter Space Definition
- Principle:Triton inference server Server Performance Verification
- Principle:OpenBMB UltraFeedback World Knowledge Injection
- Principle:Google deepmind Dm control Control Suite Environment Loading
- Principle:Bentoml BentoML Composed Pipeline Testing
- Principle:AUTOMATIC1111 Stable diffusion webui Image Gallery
Implementations
- Implementation:Kornia Kornia PSNR Loss
- Implementation:Wandb Weave Patcher Undo
- Implementation:Langchain ai Langgraph Encryption Types
- Implementation:Spotify Luigi LSFJobTask
- Implementation:Roboflow Rf detr Model Train
- Implementation:Langgenius Dify Tailwind Theme Var Define
- Implementation:Openai Openai node Transcriptions Create
- Implementation:Datajuicer Data juicer SentenceSplitMapper
- Implementation:Huggingface Optimum ImageClassificationProcessing
- Implementation:Explodinggradients Ragas Text2SQL Data Utils
Heuristics
- Heuristic:Huggingface Transformers Label Smoothing Multi Label Warning
- Heuristic:Haotian liu LLaVA Flash Attention GPU Requirement
- Heuristic:SeldonIO Seldon core Model Scheduling Preference Tip
- Heuristic:NVIDIA NeMo Aligner DPO Sequence Packing Tips
- Heuristic:Fede1024 Rust rdkafka Producer Flush Before Drop
- Heuristic:Langchain ai Langchain Warning Deprecated Langchain Classic
- Heuristic:Duckdb Duckdb Version Sync Across Files
- Heuristic:Microsoft Onnxruntime Flash Attention Optimization
- Heuristic:MaterializeInc Materialize CI Agent Prioritization
- Heuristic:Langgenius Dify Warning Deprecated Default Datasource Auth
Environments
- Environment:Helicone Helicone Cloudflare Workers Runtime
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:Apache Dolphinscheduler ZooKeeper Registry
- Environment:Vespa engine Vespa Cosign Sigstore Signing
- Environment:Alibaba ROLL CUDA GPU Environment
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Kserve Kserve Gateway API
- Environment:ChenghaoMou Text dedup Python 3 12 Environment
- Environment:Unstructured IO Unstructured All Docs
- Environment:BerriAI Litellm Python Runtime