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:Helicone Helicone Local Development Setup
- Workflow:Hiyouga LLaMA Factory PPO RLHF Training
- Workflow:TA Lib Ta lib python Abstract API Usage
- Workflow:OWASP Www project top 10 for large language model applications LLM Vulnerability Assessment
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:NVIDIA TransformerEngine FSDP Distributed Training
- Workflow:Facebookresearch Audiocraft MusicGen Text To Music Inference
- Workflow:Hiyouga LLaMA Factory DPO Preference Alignment
- Workflow:Elevenlabs Elevenlabs python Text to Speech Generation
- Workflow:ChenghaoMou Text dedup Suffix Array Deduplication
Principles
- Principle:Teamcapybara Capybara Path Assertion
- Principle:Avhz RustQuant Descriptive Statistics
- Principle:Neuml Txtai Task Wrapping
- Principle:Norrrrrrr lyn WAInjectBench JSONL Text Dataset Format
- Principle:Microsoft Playwright Analyze Test Execution
- Principle:Ollama Ollama Local Manifest Management
- Principle:Huggingface Datasets NumPy Formatting
- Principle:Langgenius Dify SecureWindowOpening
- Principle:Kubeflow Pipelines Kubernetes Cluster Preparation
- Principle:Openai Openai python Chat Response Processing
Implementations
- Implementation:Triton inference server Server L0 Metrics Test
- Implementation:SeleniumHQ Selenium DevTools ConverterFunctions
- Implementation:Haosulab ManiSkill Initialize Episode Pattern
- Implementation:PacktPublishing LLM Engineers Handbook InferenceExecutor Execute
- Implementation:Facebookresearch Audiocraft SEANet and RVQ
- Implementation:Farama Foundation Gymnasium SwimmerEnv V4
- Implementation:LMCache LMCache Server
- Implementation:Danijar Dreamerv3 Parallel Learner
- Implementation:ArroyoSystems Arroyo Worker Server
- Implementation:Openai Openai node Realtime ClientSecrets
Heuristics
- Heuristic:Axolotl ai cloud Axolotl Attention Mechanism Selection
- Heuristic:Roboflow Rf detr Batch Size Memory Tradeoff
- Heuristic:FlagOpen FlagEmbedding Dynamic Batch Size Reduction
- Heuristic:NVIDIA NeMo Aligner Adam State Offloading Tip
- Heuristic:Princeton nlp Tree of thought llm Duplicate Candidate Zeroing
- Heuristic:Volcengine Verl GPU Memory Utilization Tuning
- Heuristic:SqueezeAILab ETS Lambda Similarity Scaling
- Heuristic:PacktPublishing LLM Engineers Handbook Chunking Strategy By Content Type
- Heuristic:Haotian liu LLaVA Flash Attention GPU Requirement
- Heuristic:Dagster io Dagster Batch Size Tuning
Environments
- Environment:Diagram of thought Diagram of thought Graphviz
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Online ml River Python Runtime Environment
- Environment:Vllm project Vllm Environment Variables
- Environment:Obss Sahi Python Detection Frameworks
- Environment:Avhz RustQuant Rust Stable
- Environment:Huggingface Diffusers Attention Backends
- Environment:Treeverse LakeFS LakeFS Server Environment
- Environment:Microsoft Onnxruntime Python Inference Environment
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment