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:OpenBMB UltraFeedback Dataset Construction
- Workflow:Lance format Lance Table Optimization
- Workflow:Princeton nlp SimPO On Policy Data Generation
- Workflow:Huggingface Datasets Hub Publishing
- Workflow:MarketSquare Robotframework browser Browser Test Authoring
- Workflow:Open compass VLMEvalKit Adding Custom VLM
- Workflow:Kornia Kornia Differentiable Image Augmentation
- Workflow:ThreeSR Awesome Inference Time Scaling Manual Paper Contribution
- Workflow:Duckdb Duckdb Code Generation Pipeline
- Workflow:InternLM Lmdeploy VLM Inference Pipeline
Principles
- Principle:Webdriverio Webdriverio AsyncIterationPattern
- Principle:Explodinggradients Ragas Multi Turn Evaluation Schema
- Principle:Interpretml Interpret Classification Performance Curves
- Principle:Apache Beam Execution Monitoring
- Principle:Apache Hudi Demo Environment Cleanup
- Principle:Pyro ppl Pyro Combinatorial Distributions
- Principle:MarketSquare Robotframework browser Installation Verification
- Principle:PacktPublishing LLM Engineers Handbook Post Training Inference Validation
- Principle:Mit han lab Llm awq Fused Normalization
- Principle:Lance format Lance Row Level Updates
Implementations
- Implementation:Openai Openai python File Search Tool Model
- Implementation:Apache Shardingsphere ClusterPersistRepository Init
- Implementation:Apache Shardingsphere ShadowRule Constructor
- Implementation:Hpcaitech ColossalAI Train RM Script
- Implementation:Speechbrain Speechbrain Compute WER Tool
- Implementation:HKUDS AI Trader Agent Ainvoke
- Implementation:Iterative Dvc Utils Strictyaml
- Implementation:Ucbepic Docetl DSLRunner Load Run Save
- Implementation:ClickHouse ClickHouse Clickhouse Local Query
- Implementation:Facebookresearch Habitat lab HabitatGymWrapper
Heuristics
- Heuristic:OWASP Www project top 10 for large language model applications Warning Deprecated Markdown To PDF Convert
- Heuristic:Deepseek ai Janus CFG Weight Tuning
- Heuristic:Apache Dolphinscheduler Failover Marker TTL
- Heuristic:Princeton nlp Tree of thought llm Value Caching
- Heuristic:Webdriverio Webdriverio Exponential Backoff Retry
- Heuristic:Fastai Fastbook Discriminative Learning Rates
- Heuristic:CarperAI Trlx Reward Model Layer Freezing
- Heuristic:Mlc ai Web llm Penalty Parameter Defaults
- Heuristic:Sdv dev SDV Gaussian KDE Incompatibility
- Heuristic:Sdv dev SDV Version Compatibility
Environments
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:Unslothai Unsloth CUDA BitsAndBytes
- Environment:Evidentlyai Evidently LLM Evaluation Environment
- Environment:Ggml org Llama cpp Vulkan GPU Environment
- Environment:Fastai Fastbook NLP SpaCy Environment
- Environment:Alibaba ROLL Ascend NPU Environment
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Unstructured IO Unstructured Profiling Tools
- Environment:Datajuicer Data juicer Ray Cluster Environment
- Environment:Unstructured IO Unstructured All Docs