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:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Neuml Txtai API Deployment
- Workflow:Evidentlyai Evidently ML Model Quality Report
- Workflow:Apache Dolphinscheduler Datasource Connection Management
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Open compass VLMEvalKit Video Benchmark Evaluation
- Workflow:Cohere ai Cohere python Model Finetuning
- Workflow:Vllm project Vllm OpenAI Compatible Serving
Principles
- Principle:Bigscience workshop Petals Output Decoding
- Principle:Iterative Dvc Artifact Metadata
- Principle:OpenHands OpenHands Distributed State Management
- Principle:AUTOMATIC1111 Stable diffusion webui Text Encoder Architecture
- Principle:DataTalksClub Data engineering zoomcamp Kafka Infrastructure Setup
- Principle:Online ml River Pipeline Transformers
- Principle:Facebookresearch Audiocraft JASCO Model Loading
- Principle:Open compass VLMEvalKit MCQ Prompt Construction
- Principle:Neuml Txtai Text Tokenization
- Principle:Huggingface Optimum Meta Device Initialization
Implementations
- Implementation:Datahub project Datahub SparkOpenLineageExtensionVisitorWrapper
- Implementation:Openai Whisper Log Mel Spectrogram
- Implementation:Apache Paimon RestApi
- Implementation:Huggingface Datasets TFFormatter
- Implementation:TobikoData Sqlmesh Context Test
- Implementation:Evidentlyai Evidently Legacy Words Feature
- Implementation:Iterative Dvc Repo Get
- Implementation:LMCache LMCache Async Lookup Client
- Implementation:Online ml River Metrics Recall
- Implementation:Online ml River Imblearn ChebyshevSampler
Heuristics
- Heuristic:Datahub project Datahub Venv Copies Mode
- Heuristic:Bigscience workshop Petals NF4 Quantization Default On CUDA
- Heuristic:Huggingface Peft RSLoRA Scaling
- Heuristic:Princeton nlp SimPO Multi Seed Diversity
- Heuristic:DistrictDataLabs Yellowbrick Elbow Knee Detection Sensitivity
- Heuristic:Pyro ppl Pyro Numerical Stability Patterns
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
- Heuristic:ContextualAI HALOs Humanline Clamping
- Heuristic:Anthropics Anthropic sdk python Warning Deprecated LegacyAPIResponse
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
Environments
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:Getgauge Taiko Linux System Libraries
- Environment:Sgl project Sglang Multimodal
- Environment:Dotnet Machinelearning OneDal Acceleration
- Environment:DataExpert io Data engineer handbook Spark Iceberg Docker Environment
- Environment:DataExpert io Data engineer handbook Statsig API Environment
- Environment:Speechbrain Speechbrain HuggingFace Transformers
- Environment:LMCache LMCache CUDA GPU Runtime
- Environment:Speechbrain Speechbrain Speech Enhancement Dependencies
- Environment:BerriAI Litellm Provider API Credentials