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:Mit han lab Llm awq HuggingFace Model Export
- Workflow:Recommenders team Recommenders Algorithm Benchmarking
- Workflow:MarketSquare Robotframework browser Library Development and Release
- Workflow:Scikit learn Scikit learn Data Preprocessing Pipeline
- Workflow:Promptfoo Promptfoo Project Initialization
- Workflow:ChenghaoMou Text dedup Suffix Array Deduplication
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:Online ml River Streaming Anomaly Detection
- Workflow:Interpretml Interpret EBM Training And Prediction
Principles
- Principle:Huggingface Diffusers Training Configuration
- Principle:Webdriverio Webdriverio Async Iteration
- Principle:Kornia Kornia Deep Edge Detection
- Principle:OpenRLHF OpenRLHF Dataset Blending
- Principle:Neuml Txtai Content Conversion
- Principle:Apache Shardingsphere SPI Refresher Loading
- Principle:Recommenders team Recommenders Neural Collaborative Filtering
- Principle:Bentoml BentoML Cloud Deployment Creation
- Principle:Heibaiying BigData Notes HBase Table Creation
- Principle:Openai Openai node Response Stream Processing
Implementations
- Implementation:Online ml River Cluster CluStream
- Implementation:DataExpert io Data engineer handbook SparkSession Builder
- Implementation:Microsoft Playwright VideoRecorder
- Implementation:Ray project Ray Ray Init Cross Language
- Implementation:Open compass VLMEvalKit ConcatVideoDataset
- Implementation:OpenHands OpenHands InstallGitlabWebhooks
- Implementation:Bigscience workshop Petals DistributedMixtralConfig
- Implementation:Google deepmind Mujoco Engine Name
- Implementation:Infiniflow Ragflow MarkdownContent Component
- Implementation:Pyro ppl Pyro Abstract Infer
Heuristics
- Heuristic:Openclaw Openclaw Cache TTL Asymmetric Strategy
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
- Heuristic:TA Lib Ta lib python Unstable Period Configuration
- Heuristic:Nautechsystems Nautilus trader Parquet Row Group Tuning
- Heuristic:OpenRLHF OpenRLHF Off Policy IS Correction Tip
- Heuristic:Sktime Pytorch forecasting Learning Rate Scheduling
- Heuristic:FlagOpen FlagEmbedding Gradient Checkpointing Tip
- Heuristic:Dagster io Dagster Mandatory Ruff Formatting
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:FlowiseAI Flowise Tool Ordering Convention
Environments
- Environment:Datajuicer Data juicer GPU CUDA Environment
- Environment:Isaac sim IsaacGymEnvs IsaacGym Preview 4
- Environment:Tencent Ncnn Vulkan Environment
- Environment:LaurentMazare Tch rs Libtorch Build Environment
- Environment:Spcl Graph of thoughts OpenAI API Access
- Environment:Isaac sim IsaacGymEnvs Python CUDA Runtime
- Environment:PrefectHQ Prefect AI Integration Credentials
- Environment:Microsoft Playwright Browser Binaries Environment
- Environment:Datahub project Datahub Java Build
- Environment:NVIDIA NeMo Curator RAPIDS GPU Stack