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:Neuml Txtai Semantic Search
- Workflow:Isaac sim IsaacGymEnvs Factory Assembly Training
- Workflow:Unslothai Unsloth Model Export And Deployment
- Workflow:Lucidrains X transformers Autoregressive Language Modeling
- Workflow:Spcl Graph of thoughts GoT Sorting Pipeline
- Workflow:Scikit learn contrib Imbalanced learn Imbalanced Model Evaluation
- Workflow:Sktime Pytorch forecasting TFT Demand Forecasting
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:Diagram of thought Diagram of thought DoT Prompt Customization
- Workflow:Langgenius Dify Plugin Management
Principles
- Principle:Protectai Llm guard Malicious URL Detection
- Principle:Online ml River Streaming Signal Processing
- Principle:Heibaiying BigData Notes Storm Topology Wiring
- Principle:Tensorflow Tfjs Spatial Padding
- Principle:Rapidsai Cuml Nearest Neighbor Search
- Principle:Huggingface Datasets Streaming Download Management
- Principle:ClickHouse ClickHouse SIMD String Hashing
- Principle:EvolvingLMMs Lab Lmms eval Data Sharding
- Principle:Apache Hudi Table Schema Definition
- Principle:Intel Ipex llm DPO Model Loading
Implementations
- Implementation:Predibase Lorax Flash Phi3 Modeling
- Implementation:Interpretml Interpret Term
- Implementation:NVIDIA DALI KernelTraits
- Implementation:ArroyoSystems Arroyo Create Connection Page
- Implementation:SeleniumHQ Selenium Closure Events
- Implementation:Langchain ai Langgraph StateGraph Compile With Interrupts
- Implementation:Puppeteer Puppeteer Cdp PredefinedNetworkConditions
- Implementation:Microsoft DeepSpeedExamples Tensor Parallel Utilities
- Implementation:Sgl project Sglang Get Model Loader
- Implementation:Ggml org Llama cpp Semantic Check
Heuristics
- Heuristic:ClickHouse ClickHouse Jemalloc Production Requirement
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:Heibaiying BigData Notes Hive ORC Parquet Storage Tip
- Heuristic:Google research Deduplicate text datasets HACKSIZE Overlap Buffer
- Heuristic:Tencent Ncnn Thread Count Tuning
- Heuristic:Marker Inc Korea AutoRAG Empty Result Fallback
- Heuristic:ChenghaoMou Text dedup False Positive Verification Tradeoff
- Heuristic:TobikoData Sqlmesh Forward Only Safety
- Heuristic:EvolvingLMMs Lab Lmms eval Limit Flag Testing Only
- Heuristic:Arize ai Phoenix Warning Deprecated VertexAIModel
Environments
- Environment:Truera Trulens Python Core Environment
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Neuml Txtai GPU Accelerator Detection
- Environment:Microsoft Autogen Python Runtime Environment
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:Huggingface Datasets JAX Integration
- Environment:Hiyouga LLaMA Factory Core Python GPU Environment
- Environment:Alibaba ROLL vLLM Inference Environment
- Environment:Langfuse Langfuse Docker Infrastructure
- Environment:Datajuicer Data juicer GPU CUDA Environment