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:Nightwatchjs Nightwatch Custom Commands And Assertions
- Workflow:Alibaba ROLL Supervised Finetuning Pipeline
- Workflow:Apache Dolphinscheduler RPC Service Communication
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:OpenHands OpenHands SaaS Server Assembly
- Workflow:Huggingface Peft LoRA Embedding Semantic Search
- Workflow:LLMBook zh LLMBook zh github io LoRA Finetuning
- Workflow:Duckdb Duckdb Building From Source
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Predibase Lorax Structured JSON Output
Principles
- Principle:Apache Hudi Clustering Commit
- Principle:Iamhankai Forest of Thought Tree of Thought Search
- Principle:Roboflow Rf detr Model Deployment
- Principle:Fastai Fastbook Feature Importance
- Principle:Google deepmind Mujoco Restrict Optimization
- Principle:ChenghaoMou Text dedup False Positive Verification SimHash
- Principle:Deepspeedai DeepSpeed SP Data Preparation
- Principle:Langgenius Dify Node Composition
- Principle:PacktPublishing LLM Engineers Handbook HuggingFace Dataset Publishing
- Principle:Huggingface Diffusers Training Model Loading
Implementations
- Implementation:Datajuicer Data juicer ImageAspectRatioFilter
- Implementation:TobikoData Sqlmesh Metadata Component
- Implementation:Openai Openai python Response Custom Tool Call Input Delta
- Implementation:BerriAI Litellm Provider Endpoints Support
- Implementation:Danijar Dreamerv3 Combined Launcher
- Implementation:Apache Flink BulkDecodingFormat
- Implementation:Mistralai Client python Mistral Init
- Implementation:ArroyoSystems Arroyo Pipeline Graph
- Implementation:SeleniumHQ Selenium Closure Promise
- Implementation:Groq Groq python Model Type
Heuristics
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
- Heuristic:Microsoft DeepSpeedExamples RLHF Hyperparameter Guide
- Heuristic:AnswerDotAI RAGatouille In Memory Reranking Limits
- Heuristic:PacktPublishing LLM Engineers Handbook Dataset Generation Quality Filters
- Heuristic:Romsto Speculative Decoding Shared Tokenizer Requirement
- Heuristic:Vllm project Vllm GPU Memory Utilization Tuning
- Heuristic:Astronomer Astronomer cosmos Cache Strategy Optimization
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Apache Dolphinscheduler JDBC Security Blocklist
- Heuristic:Microsoft LoRA Warning Deprecated Legacy Examples
Environments
- Environment:Google deepmind Dm control GLFW Desktop Rendering
- Environment:Hiyouga LLaMA Factory Distributed Training Environment
- Environment:Openai CLIP Python Dependencies
- Environment:Sail sg LongSpec Inference Environment
- Environment:Truera Trulens OpenAI Provider Environment
- Environment:Groq Groq python Python Groq SDK
- Environment:Mbzuai oryx Awesome LLM Post training Git CLI
- Environment:Allenai Open instruct CUDA GPU Training
- Environment:LLMBook zh LLMBook zh github io PyTorch CUDA GPU Environment
- Environment:Fastai Fastbook Jupyter Notebook Environment