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:Vespa engine Vespa Config subscription lifecycle
- Workflow:Sgl project Sglang Frontend Language Multi Turn Chat
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Spotify Luigi Hadoop MapReduce Pipeline
- Workflow:Obss Sahi COCO Evaluation
- Workflow:Promptfoo Promptfoo LLM Evaluation
- Workflow:Unslothai Unsloth GRPO Reinforcement Learning
- Workflow:Openai Evals Creating a model graded eval
- Workflow:Pyro ppl Pyro MCMC Inference
- Workflow:Spotify Luigi Spark Processing Pipeline
Principles
- Principle:Rapidsai Cuml Multiclass Classification Strategy
- Principle:Scikit learn contrib Imbalanced learn Sphinx Documentation Configuration
- Principle:Cleanlab Cleanlab Object Detection Visualization
- Principle:Cleanlab Cleanlab Object Detection Quality Scoring
- Principle:OpenRLHF OpenRLHF Prompt Dataset Construction
- Principle:Protectai Llm guard Input Scanner Factory Pattern
- Principle:Openai Evals Few Shot Prompting
- Principle:Triton inference server Server Source Build
- Principle:Princeton nlp SimPO Environment Setup
- Principle:Getgauge Taiko Button Selection
Implementations
- Implementation:DistrictDataLabs Yellowbrick GridSearchColorPlot
- Implementation:Anthropics Anthropic sdk python Pydantic Compat
- Implementation:Microsoft Onnxruntime DataLoader Init
- Implementation:Risingwavelabs Risingwave SinkValidationHandler
- Implementation:Alibaba ROLL Diffusion DeepSpeed Cluster
- Implementation:Openai Openai node Jobs Create
- Implementation:OpenHands OpenHands SPAStaticFiles Mount
- Implementation:Anthropics Anthropic sdk python BetaMessage
- Implementation:Hiyouga LLaMA Factory WebUI Data Component
- Implementation:Duckdb Duckdb Parquet Types
Heuristics
- Heuristic:Explodinggradients Ragas Failed Metrics Return NaN
- Heuristic:Onnx Onnx Protobuf 2GB Limit Workaround
- Heuristic:Openai Evals Model Graded Eval Design
- Heuristic:Apache Druid Capability Detection Strategy
- Heuristic:Apache Shardingsphere Shadow Routing Hint First Fallback
- Heuristic:Facebookresearch Habitat lab Warning Deprecated Legacy UI System
- Heuristic:TobikoData Sqlmesh Forward Only Safety
- Heuristic:Openai Openai agents python MCP Server Lifecycle Management
- Heuristic:SeleniumHQ Selenium Cross Binding Consistency Check
- Heuristic:Run llama Llama index Worker Count Configuration
Environments
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference
- Environment:Datahub project Datahub Spark Lineage Environment
- Environment:Explodinggradients Ragas Optional Metrics Environment
- Environment:ChenghaoMou Text dedup Python 3 12 Environment
- Environment:Scikit learn Scikit learn OpenMP Thread Configuration
- Environment:Lucidrains X transformers Python Environment
- Environment:Volcengine Verl CUDA GPU Environment
- Environment:Interpretml Interpret Visualization Environment
- Environment:Isaac sim IsaacGymEnvs Python CUDA Runtime
- Environment:Microsoft Agent framework API Credentials