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:LLMBook zh LLMBook zh github io LoRA Finetuning
- Workflow:Speechbrain Speechbrain Speech Separation Training
- Workflow:Predibase Lorax Server Deployment
- Workflow:TobikoData Sqlmesh Plan and apply deployment
- Workflow:Openai Openai agents python Multi Agent Handoff
- Workflow:Huggingface Diffusers DreamBooth Personalization
- Workflow:Lance format Lance Full Text Search
- Workflow:Junyanz Pytorch CycleGAN and pix2pix Pretrained Inference
- Workflow:Huggingface Alignment handbook Multi Stage Post Training
- Workflow:Apache Dolphinscheduler Datasource Plugin Development
Principles
- Principle:Romsto Speculative Decoding Rejection Sampling Adjustment
- Principle:Microsoft Playwright Execute Automation Command
- Principle:Sdv dev SDV Fixed Combinations Constraint
- Principle:Intel Ipex llm DPO Data Preparation
- Principle:Langchain ai Langchain Provider API Invocation
- Principle:Huggingface Diffusers Training Dataset Preparation
- Principle:LaurentMazare Tch rs Darknet Model Building
- Principle:Nautechsystems Nautilus trader Historical Data Wrangling
- Principle:Eventual Inc Daft Documentation Notebook Generation
- Principle:Promptfoo Promptfoo CI Notification
Implementations
- Implementation:Getgauge Taiko ListItemWrapper
- Implementation:Apache Paimon BlockReader
- Implementation:Junyanz Pytorch CycleGAN and pix2pix Visualizer
- Implementation:Microsoft Onnxruntime TrainingSession
- Implementation:Facebookresearch Habitat lab GuiDrawer
- Implementation:Neuml Txtai IVFSparse ANN
- Implementation:Pyro ppl Pyro RSA Hyperbole
- Implementation:Guardrails ai Guardrails Schema Parser
- Implementation:Run llama Llama index IndexStructType
- Implementation:DistrictDataLabs Yellowbrick MissingValuesBar
Heuristics
- Heuristic:Apache Dolphinscheduler Netty Thread Sizing
- Heuristic:Lance format Lance Vector Index Tuning
- Heuristic:OpenHands OpenHands Clustered Race Condition Prevention
- Heuristic:Scikit learn Scikit learn Convergence Warning Handling
- Heuristic:ThreeSR Awesome Inference Time Scaling Duplicate Detection By Title
- Heuristic:Microsoft DeepSpeedExamples RLHF Hyperparameter Guide
- Heuristic:SeleniumHQ Selenium Explicit Over Implicit Waits
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:Protectai Modelscan Graceful Scanner Degradation
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
Environments
- Environment:Mlc ai Web llm WebGPU Browser Runtime
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:ClickHouse ClickHouse Linux Build Environment
- Environment:Confident ai Deepeval Python 3 9 Runtime
- Environment:Truera Trulens Snowflake Connector Environment
- Environment:NVIDIA NeMo Curator NVIDIA DALI
- Environment:Wandb Weave Trace Server Infrastructure
- Environment:Mlflow Mlflow OpenAI LLM Integration Environment
- Environment:Triton inference server Server GPU CUDA Runtime
- Environment:Farama Foundation Gymnasium JAX Functional Backend