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:Eric mitchell Direct preference optimization DPO Preference Training
- Workflow:Rapidsai Cuml Sklearn Zero Code Acceleration
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:Promptfoo Promptfoo Red Team Security Scan
- Workflow:CARLA simulator Carla Building from Source
- Workflow:Dotnet Machinelearning Time Series Forecasting
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Anthropics Anthropic sdk python Streaming Message Interaction
- Workflow:Googleapis Python genai Function Calling and Tools
- Workflow:Getgauge Taiko Interactive Test Recording
Principles
- Principle:Spotify Luigi External Data Sources
- Principle:Anthropics Anthropic sdk python Streaming Structured Output
- Principle:Ollama Ollama Integrity Verification
- Principle:Langfuse Langfuse Data Streaming from ClickHouse
- Principle:MaterializeInc Materialize Composition Execution
- Principle:Google deepmind Mujoco Resource Cleanup
- Principle:Google research Deduplicate text datasets Suffix Array Construction
- Principle:Open compass VLMEvalKit Model Registry
- Principle:Vespa engine Vespa Subscriber Shutdown
- Principle:EvolvingLMMs Lab Lmms eval Dataset Preparation
Implementations
- Implementation:Explodinggradients Ragas RankingMetric Class
- Implementation:Google deepmind Mujoco MJWarp Constraint
- Implementation:Obss Sahi GreedyNMM Postprocess
- Implementation:Apache Druid Filter Pattern Helpers
- Implementation:DevExpress Testcafe TestController TypeDefs
- Implementation:NVIDIA NeMo Curator DomainClassifier
- Implementation:Tensorflow Serving Caching Manager Test
- Implementation:Huggingface Diffusers Prepare Control Image
- Implementation:Run llama Llama index CustomLLM
- Implementation:CARLA simulator Carla Python Commands Bindings
Heuristics
- Heuristic:Speechbrain Speechbrain Dynamic Mixing Parameters
- Heuristic:Astronomer Astronomer cosmos Cache Strategy Optimization
- Heuristic:VainF Torch Pruning Pruning Ratio vs Parameter Ratio
- Heuristic:BerriAI Litellm Batch Size Flush Interval Tuning
- Heuristic:Infiniflow Ragflow Hybrid Search Fallback Strategy
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:Obss Sahi Warning Deprecated Legacy NMS
- Heuristic:Marker Inc Korea AutoRAG Passage Filter Safety Minimum
- Heuristic:Datahub project Datahub Validation Across All APIs
- Heuristic:SeldonIO Seldon core Model Scheduling Preference Tip
Environments
- Environment:Langfuse Langfuse Docker Infrastructure
- Environment:Langgenius Dify Python Backend Environment
- Environment:Tensorflow Serving Kubernetes Deployment Environment
- Environment:Apache Spark Python Environment
- Environment:Vllm project Vllm Python Dependencies
- Environment:Bitsandbytes foundation Bitsandbytes ROCm AMD Environment
- Environment:Microsoft DeepSpeedExamples SuperOffload Runtime
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Sgl project Sglang Python Dependencies