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:Neuml Txtai Semantic Search
- Workflow:Roboflow Rf detr Custom Dataset Finetuning
- Workflow:PrefectHQ Prefect AI Data Analyst Agent
- Workflow:Nautechsystems Nautilus trader Live trading deployment
- Workflow:Lucidrains X transformers Autoregressive Language Modeling
- Workflow:Langfuse Langfuse Trace ingestion pipeline
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Microsoft Autogen Multi Agent Conversation
- Workflow:Run llama Llama index Embedding Finetuning
- Workflow:Confident ai Deepeval Synthetic Dataset Generation
Principles
- Principle:Ggml org Llama cpp GrammarConstrained
- Principle:Vespa engine Vespa Runtime Level Control
- Principle:SeleniumHQ Selenium Bazel Build Verification
- Principle:PrefectHQ Prefect Durable AI Execution
- Principle:Astronomer Astronomer cosmos Render Configuration
- Principle:Dotnet Machinelearning Binary Model Evaluation
- Principle:Zai org CogVideo Vector Quantization
- Principle:OpenHands OpenHands Sandbox Cleanup
- Principle:Bentoml BentoML Model Cloud Sync
- Principle:Langchain ai Langgraph Multi Agent Research Pattern
Implementations
- Implementation:EvolvingLMMs Lab Lmms eval WildVision Bench Evaluation Utils
- Implementation:Open compass VLMEvalKit EgoExoBench Utils
- Implementation:Microsoft Playwright WkProvisionalPage
- Implementation:Allenai Open instruct AutoModelForSequenceClassification From Pretrained
- Implementation:Online ml River Metrics SMAPE
- Implementation:Open compass VLMEvalKit VCRBench
- Implementation:Guardrails ai Guardrails Guard Load
- Implementation:Open compass VLMEvalKit Check Command
- Implementation:FlowiseAI Flowise AddEditDatasetDialog
- Implementation:Intel Ipex llm IpexLLM From Model Id
Heuristics
- Heuristic:Unstructured IO Unstructured Multi Python Matrix
- Heuristic:Huggingface Diffusers Guidance Scale Defaults
- Heuristic:InternLM Lmdeploy Backend Selection Strategy
- Heuristic:NVIDIA NeMo Aligner PPO NCCL Algorithm Setting
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:NVIDIA DALI Last Batch Policy Selection
- Heuristic:Unslothai Unsloth Gradient Checkpointing Modes
- Heuristic:Bentoml BentoML Warning Deprecated Server Module
- Heuristic:Scikit learn contrib Imbalanced learn Sampling Strategy Selection
- Heuristic:Testtimescaling Testtimescaling github io Hardcoded IDs vs Registry
Environments
- Environment:Heibaiying BigData Notes Hadoop CDH Environment
- Environment:Confident ai Deepeval Python 3 9 Runtime
- Environment:Confident ai Deepeval LLM Provider Credentials
- Environment:ClickHouse ClickHouse CI Docker Environment
- Environment:EvolvingLMMs Lab Lmms eval Server Mode Environment
- Environment:MaterializeInc Materialize Dbt Materialize Runtime
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:LMCache LMCache NIXL Transfer Library
- Environment:FMInference FlexLLMGen HuggingFace Access