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:Hiyouga LLaMA Factory Model Inference and Serving
- Workflow:Googleapis Python genai Model Fine Tuning
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:LMCache LMCache P2P KV Cache Sharing
- Workflow:Cypress io Cypress Local Development Environment
- Workflow:Scikit learn Scikit learn Ensemble Model Building
- Workflow:Lucidrains X transformers Encoder Decoder Sequence to Sequence
- Workflow:Langgenius Dify Visual Workflow Builder
- Workflow:Princeton nlp Tree of thought llm Adding new task
- Workflow:SeleniumHQ Selenium Selenium Grid Deployment
Principles
- Principle:Diagram of thought Diagram of thought Convergence Assessment
- Principle:Interpretml Interpret Tree Interpretation
- Principle:MarketSquare Robotframework browser ES2015 Module Transpilation
- Principle:Online ml River Pipeline Transformers
- Principle:Online ml River Online Naive Bayes
- Principle:OpenGVLab InternVL Multimodal Data Preparation
- Principle:Pyro ppl Pyro MCMC Numerical Methods
- Principle:Google deepmind Mujoco BVH Acceleration
- Principle:Openai Evals Solver Implementation
- Principle:LaurentMazare Tch rs Sparse Adam Optimization
Implementations
- Implementation:Speechbrain Speechbrain Train SLURP Direct
- Implementation:Google deepmind Mujoco User API Header
- Implementation:Duckdb Duckdb LZ4 Compression
- Implementation:SeleniumHQ Selenium Keys
- Implementation:Haosulab ManiSkill Convert To LeRobot CLI
- Implementation:Neuml Txtai Agent Call
- Implementation:Huggingface Diffusers SDXL Pipeline Call
- Implementation:Openai Openai python Fine Tuning Job Succeeded Webhook
- Implementation:Mlflow Mlflow Register Model
- Implementation:Neuml Txtai Pipeline Constructors
Heuristics
- Heuristic:Huggingface Peft LoRA Default Configuration
- Heuristic:Arize ai Phoenix Warning Deprecated HallucinationEvaluator
- Heuristic:Mage ai Mage ai Batch Size Tuning
- Heuristic:SeleniumHQ Selenium FindElements For Absence Check
- Heuristic:Groq Groq python Timeout Configuration
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
- Heuristic:ARISE Initiative Robomimic Checkpoint Selection Strategy
- Heuristic:Open compass VLMEvalKit SKIP ERR For Graceful Inference
- Heuristic:Lm sys FastChat Flash Attention GPU Requirements
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
Environments
- Environment:Apache Hudi Java Maven Build Environment
- Environment:Intel Ipex llm Windows Environment
- Environment:OpenGVLab InternVL PyTorch CUDA
- Environment:LMCache LMCache NIXL Transfer Library
- Environment:Spcl Graph of thoughts Local LLaMA GPU Inference
- Environment:Interpretml Interpret Visualization Environment
- Environment:Protectai Llm guard API Server Deployment
- Environment:Arize ai Phoenix Frontend Node 22
- Environment:Facebookresearch Audiocraft AudioCraft Environment Variables
- Environment:Alibaba ROLL Diffusion Video Environment