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:MaterializeInc Materialize Docker Image Build
- Workflow:Sail sg LongSpec Long Context Evaluation
- Workflow:Dagster io Dagster ML Pipeline
- Workflow:Puppeteer Puppeteer Browser Installation And Management
- Workflow:Deepset ai Haystack Document Indexing Pipeline
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:Apache Paimon Vector Similarity Search
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Openclaw Openclaw Gateway Operations And Diagnostics
- Workflow:Eventual Inc Daft Distributed UDF Processing
Principles
- Principle:SeldonIO Seldon core Model Artifact Preparation
- Principle:Huggingface Trl GRPO Prompt Dataset Loading
- Principle:AUTOMATIC1111 Stable diffusion webui Face restoration
- Principle:Tensorflow Tfjs Causal Language Model Head
- Principle:Microsoft Onnxruntime Distributed Training Loop
- Principle:Ollama Ollama GGUF Model Conversion Phi3
- Principle:Kserve Kserve Graph Request Routing
- Principle:FMInference FlexLLMGen Prediction Evaluation Metrics
- Principle:MarketSquare Robotframework browser Node Dependency Initialization
- Principle:Avhz RustQuant Volatility Surface
Implementations
- Implementation:Google deepmind Mujoco MJX Collision Types
- Implementation:Infiniflow Ragflow NextSearchHooks
- Implementation:Datajuicer Data juicer DataJuicerTestCaseBase Pattern
- Implementation:Dotnet Machinelearning AliasMultinomialRng
- Implementation:Run llama Llama index StructuredLLMRerank
- Implementation:BerriAI Litellm Passthrough API
- Implementation:Scikit learn Scikit learn ImageFeatureExtraction
- Implementation:Avhz RustQuant Distribution Trait
- Implementation:Eventual Inc Daft Session Set Catalog
- Implementation:Kserve Kserve AlibiExplainer
Heuristics
- Heuristic:Sktime Pytorch forecasting Learning Rate Scheduling
- Heuristic:Vibrantlabsai Ragas Temperature Sampling Strategy
- Heuristic:Elevenlabs Elevenlabs python Client Timeout Configuration
- Heuristic:Cleanlab Cleanlab KNN Distance Metric Selection
- Heuristic:Langgenius Dify Celery Queue Separation
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
- Heuristic:ClickHouse ClickHouse ThinLTO Build Tradeoffs
- Heuristic:Evidentlyai Evidently Column Type Inference Rules
- Heuristic:Kserve Kserve Prefix Cache Consistency
- Heuristic:LLMBook zh LLMBook zh github io LoRA Initialization Strategy
Environments
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:Lance format Lance SIMD And Platform Requirements
- Environment:Sgl project Sglang Prometheus
- Environment:Open compass VLMEvalKit Data Storage Environment
- Environment:Vllm project Vllm CUDA Hopper
- Environment:Huggingface Datatrove Processing Dependencies
- Environment:Bigscience workshop Petals Python Transformers
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:Fastai Fastbook CUDA GPU Environment
- Environment:Ray project Ray Docker GPU Environment