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:Mlc ai Web llm Web Worker Deployment
- Workflow:Lakeraai Pint benchmark Custom Dataset Benchmarking
- Workflow:Lm sys FastChat Vicuna SFT Finetuning
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Tensorflow Serving Kubernetes Deployment
- Workflow:DataExpert io Data engineer handbook AB Experimentation Server
- Workflow:Fastai Fastbook NLP Text Classification
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Mit han lab Llm awq AWQ Model Evaluation
Principles
- Principle:Haosulab ManiSkill RL Evaluation Checkpointing
- Principle:Ray project Ray Release Validation Testing
- Principle:Apache Dolphinscheduler Workflow Triggering
- Principle:Facebookresearch Audiocraft Language Model Export
- Principle:NVIDIA NeMo Aligner SteerLM Training
- Principle:Microsoft Agent framework YAML Agent Loading
- Principle:Cypress io Cypress System Test Validation
- Principle:Spotify Luigi Database Data Loading
- Principle:Huggingface Trl PEFT LoRA Configuration SFT
- Principle:Tensorflow Serving Loader Abstraction
Implementations
- Implementation:ARISE Initiative Robosuite Demo Sensor Corruption
- Implementation:Facebookresearch Audiocraft Evaluation Metrics
- Implementation:Triton inference server Server GenQaDynaSequenceImplicitModels
- Implementation:Infiniflow Ragflow Parser Chunk Methods
- Implementation:Microsoft DeepSpeedExamples Net DeepSpeed
- Implementation:Guardrails ai Guardrails Schema Parser
- Implementation:Alibaba MNN PyMNN Module Forward
- Implementation:Scikit learn Scikit learn AgglomerativeClustering
- Implementation:DataTalksClub Data engineering zoomcamp Redpanda Ride Model
- Implementation:Microsoft Playwright BidiPdf
Heuristics
- Heuristic:Openai Openai python Streaming Resource Management
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
- Heuristic:ContextualAI HALOs Reference Logprob Caching
- Heuristic:Microsoft Onnxruntime Graph Optimization Level Selection
- Heuristic:Microsoft Autogen Agent Thread Safety
- Heuristic:Openai Whisper Median Word Duration Clamping
- Heuristic:Alibaba ROLL Sequence Packing Alignment
- Heuristic:Microsoft Autogen Parallel Tool Call Safety
- Heuristic:Langchain ai Langchain Error Context Preservation
- Heuristic:ThreeSR Awesome Inference Time Scaling Duplicate Detection By Title
Environments
- Environment:Mlflow Mlflow OpenAI LLM Integration Environment
- Environment:Pola rs Polars Python Runtime Environment
- Environment:Elevenlabs Elevenlabs python FFmpeg Mpv
- Environment:Evidentlyai Evidently Spark Engine Environment
- Environment:SeleniumHQ Selenium Contributor Development Environment
- Environment:Predibase Lorax Model Source Credentials
- Environment:DataTalksClub Data engineering zoomcamp Dlt BigQuery Environment
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Nautechsystems Nautilus trader Arrow Parquet Serialization
- Environment:Spotify Luigi Tornado Web Server