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:Neuml Txtai Workflow Orchestration
- Workflow:EvolvingLMMs Lab Lmms eval Distributed Multi GPU Evaluation
- Workflow:ChenghaoMou Text dedup SimHash Deduplication
- Workflow:Apache Hudi Flink Table Clustering
- Workflow:Liu00222 Open Prompt Injection Detection Localization Defense
- Workflow:Huggingface Trl Reward Model Training
- Workflow:Microsoft Semantic kernel Vector Store RAG Pipeline
- Workflow:Treeverse LakeFS Data Version Control With Branches
- Workflow:Datajuicer Data juicer Text Data Processing Pipeline
- Workflow:Mistralai Client python Finetuning Job Management
Principles
- Principle:Treeverse LakeFS Hook Guarded Merge
- Principle:Huggingface Trl PPO Model Saving and Evaluation
- Principle:Langgenius Dify Datasource Node Configuration
- Principle:AUTOMATIC1111 Stable diffusion webui Fair Task Scheduling
- Principle:Mlflow Mlflow Trace Search and Analysis
- Principle:BerriAI Litellm Message Redaction
- Principle:Roboflow Rf detr ONNX Model Export
- Principle:Langgenius Dify Prompt Template Design
- Principle:Sktime Pytorch forecasting TimeXer Architecture
- Principle:Nightwatchjs Nightwatch BDD Style Expect Assertions
Implementations
- Implementation:Apache Paimon BinaryRow
- Implementation:Cohere ai Cohere python HttpResponse
- Implementation:DevExpress Testcafe AssertionExecutor
- Implementation:Openai Openai python Datetime Parse
- Implementation:Google deepmind Mujoco User Composite
- Implementation:Shiyu coder Kronos Config Init
- Implementation:Heibaiying BigData Notes Hive Partition and Bucket Config
- Implementation:Arize ai Phoenix Create Evaluator Decorator
- Implementation:Truera Trulens Otel Record Viewer Dependencies
- Implementation:Turboderp org Exllamav2 ExLlamaV2SelectFilter
Heuristics
- Heuristic:Hpcaitech ColossalAI Warning Deprecated Ray Detached PPO
- Heuristic:OpenRLHF OpenRLHF Gradient Checkpointing Memory Tip
- Heuristic:Langchain ai Langchain Pydantic V2 Configuration Tips
- Heuristic:DataTalksClub Data engineering zoomcamp CSV Chunk Size Optimization
- Heuristic:Openai Openai node Browser Safety Guard
- Heuristic:Ray project Ray Autoscaling Delay Tuning
- Heuristic:Spcl Graph of thoughts GoT Decompose Sort Merge Strategy
- Heuristic:Treeverse LakeFS S3 Multipart Size Constraint
- Heuristic:SeldonIO Seldon core Model Load Timeout Tip
- Heuristic:CrewAIInc CrewAI RAG Search Defaults
Environments
- Environment:Alibaba MNN ARM Mobile Environment
- Environment:Sgl project Sglang Python Dependencies
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:CrewAIInc CrewAI Optional Provider Dependencies
- Environment:Huggingface Datatrove S3 Storage Environment
- Environment:Openai Openai node WebSocket Dependency
- Environment:Google deepmind Dm control GLFW Desktop Rendering
- Environment:Promptfoo Promptfoo Node Runtime
- Environment:OpenGVLab InternVL PEFT LoRA