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:AnswerDotAI RAGatouille In Memory Retrieval
- Workflow:OpenBMB UltraFeedback Dataset Construction
- Workflow:Liu00222 Open Prompt Injection Prompt Injection Experiment
- Workflow:OpenRLHF OpenRLHF PPO Ray Training
- Workflow:Gretelai Gretel synthetics DataFrame Batch Synthesis
- Workflow:Vibrantlabsai Ragas Testset Generation
- Workflow:Openclaw Openclaw Docker Deployment
- Workflow:Datahub project Datahub Docker Quickstart Deployment
- Workflow:InternLM Lmdeploy LLM Offline Batch Inference
- Workflow:Lance format Lance Full Text Search
Principles
- Principle:FlowiseAI Flowise Authentication
- Principle:Bentoml BentoML Model Loading From Store
- Principle:Turboderp org Exllamav2 Quantization Sensitivity Measurement
- Principle:ClickHouse ClickHouse Server Health Verification
- Principle:Shiyu coder Kronos Autoregressive Token Generation
- Principle:Microsoft Semantic kernel Vector Similarity Search
- Principle:Webdriverio Webdriverio BrowserStack Capability Management
- Principle:Google research Deduplicate text datasets Self Similar Duplicate Detection
- Principle:Princeton nlp Tree of thought llm Thought Evaluation
- Principle:Datahub project Datahub Spark Lineage Configuration
Implementations
- Implementation:Pyro ppl Pyro TensorUtils
- Implementation:Microsoft Onnxruntime OrtCUDAProviderOptions
- Implementation:SeleniumHQ Selenium ExternalProcess
- Implementation:Datajuicer Data juicer ExtractNicknameMapper
- Implementation:Fastai Fastbook Numericalize
- Implementation:Pyro ppl Pyro CoalescentTimes
- Implementation:Interpretml Interpret Powerlift TaskMeasures
- Implementation:Datahub project Datahub MergeIntoCommandInputDatasetBuilder
- Implementation:Mage ai Mage ai Chargebee Base Stream
- Implementation:Openai Openai node Batches Resource
Heuristics
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
- Heuristic:Onnx Onnx Shape Inference Limitations
- Heuristic:Iamhankai Forest of Thought Early Stop Majority Vote
- Heuristic:Huggingface Datasets Parquet Shard Sizing
- Heuristic:Iterative Dvc Run Cache Restoration Strategy
- Heuristic:Avhz RustQuant Finite Difference Grid Sizing
- Heuristic:OpenGVLab InternVL Dynamic Resolution Tiling
- Heuristic:Huggingface Alignment handbook Liger Kernel Memory
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Huggingface Open r1 Test Batch Early Termination
Environments
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Apache Airflow Python Runtime Environment
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:OpenRLHF OpenRLHF vLLM Environment
- Environment:Shiyu coder Kronos DDP Multi GPU Environment
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Alibaba ROLL Diffusion Video Environment
- Environment:Vibrantlabsai Ragas LLM Provider Credentials
- Environment:Online ml River Build Toolchain
- Environment:Sgl project Sglang Web