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 Inference and Quantization
- Workflow:Mlflow Mlflow Model Logging and Registry
- Workflow:Alibaba ROLL DPO Training Pipeline
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:AnswerDotAI RAGatouille ColBERT Training
- Workflow:Marker Inc Korea AutoRAG Data Creation Pipeline
- Workflow:TobikoData Sqlmesh Plan and apply deployment
- Workflow:Astronomer Astronomer cosmos TaskGroup dbt integration
- Workflow:Openai Openai agents python Guardrails Secured Agent
Principles
- Principle:Fastai Fastbook Transfer Learning
- Principle:Volcengine Verl Rule Based Reward Computation
- Principle:Tencent Ncnn Pixel Geometry Transform
- Principle:Openai Whisper Median Filtering
- Principle:Huggingface Datasets Column Name Inspection
- Principle:OpenHands OpenHands Permission Check
- Principle:Huggingface Alignment handbook Tokenizer Loading
- Principle:Apache Paimon Ray Data Source Reading
- Principle:OpenBMB UltraFeedback Principle Sampling
- Principle:DataTalksClub Data engineering zoomcamp Dlt Resource Definition
Implementations
- Implementation:Haotian liu LLaVA Apply Delta
- Implementation:AUTOMATIC1111 Stable diffusion webui CondFunc
- Implementation:Tencent Ncnn Extractor Vulkan Compute
- Implementation:SeleniumHQ Selenium BuildInfo
- Implementation:Ggml org Ggml Cpu riscv quants
- Implementation:Tensorflow Serving Remote Predict Ops
- Implementation:PacktPublishing LLM Engineers Handbook DatasetGenerator Generate
- Implementation:TobikoData Sqlmesh Model PlanAction
- Implementation:Farama Foundation Gymnasium JaxToNumpy
- Implementation:Langgenius Dify I18n Translation Data
Heuristics
- Heuristic:Neuml Txtai MacOS Stability Workarounds
- Heuristic:Allenai Open instruct Logprob Clamping
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:Lance format Lance Fragment Sizing Strategy
- Heuristic:Protectai Modelscan Unknown Opcodes Assume Critical
- Heuristic:Microsoft DeepSpeedExamples RLHF Hyperparameter Guide
- Heuristic:SeldonIO Seldon core Model Load Timeout Tip
- Heuristic:Obss Sahi Auto Slice Resolution
- Heuristic:Huggingface Alignment handbook DPO Beta Selection
- Heuristic:Facebookresearch Habitat lab DDPPO Straggler Preemption
Environments
- Environment:Dotnet Machinelearning TorchSharp Environment
- Environment:Microsoft BIPIA DeepSpeed Finetuning Environment
- Environment:Datahub project Datahub Python 3 10 Ingestion Environment
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:OWASP Www project top 10 for large language model applications GenAI Red Team Environment
- Environment:Kserve Kserve Cert Manager
- Environment:Protectai Modelscan Python Core Runtime
- Environment:Alibaba ROLL SGLang Inference Environment
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:SqueezeAILab ETS Evaluation Python Stack