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:Huggingface Diffusers ControlNet Guided Generation
- Workflow:Mlc ai Mlc llm REST API Serving
- Workflow:Onnx Onnx Model Composition
- Workflow:OWASP Www project top 10 for large language model applications Vulnerability Translation
- Workflow:Mistralai Client python OCR Document Processing
- Workflow:Guardrails ai Guardrails Custom Validator Development
- Workflow:BerriAI Litellm Proxy Server Deployment
- Workflow:Langchain ai Langchain Adding Partner Integration
- Workflow:PacktPublishing LLM Engineers Handbook Feature Engineering
- Workflow:ARISE Initiative Robosuite Human Demonstration Collection
Principles
- Principle:Tensorflow Tfjs Pretrained Weight Loading
- Principle:Huggingface Datatrove JSONL Data Reading
- Principle:Cohere ai Cohere python Batch Embedding Jobs
- Principle:Protectai Llm guard Sensitive Data Detection
- Principle:Marker Inc Korea AutoRAG Evaluator Initialization
- Principle:Lm sys FastChat HuggingFace Pipeline Inference
- Principle:Eric mitchell Direct preference optimization Concatenated Forward Pass
- Principle:Unstructured IO Unstructured Section Aware Chunking
- Principle:Cypress io Cypress Component Testing Configuration
- Principle:Langchain ai Langgraph Task Definition
Implementations
- Implementation:Zai org CogVideo Parallel Inference xDiT
- Implementation:Bentoml BentoML Framework Keras
- Implementation:Mbzuai oryx Awesome LLM Post training Json Dump Progressive
- Implementation:Sgl project Sglang Sgl Runtime Init
- Implementation:Ggml org Ggml Sam build fast graph
- Implementation:Sgl project Sglang MoE Ops
- Implementation:NVIDIA NeMo Curator ArXiv URLGenerator
- Implementation:Google deepmind Mujoco Filament Builtins
- Implementation:Sgl project Sglang Sgl Kernel Init
- Implementation:Lm sys FastChat Build Side By Side Arena Anony UI
Heuristics
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Test Train Option Consistency
- Heuristic:EvolvingLMMs Lab Lmms eval Memory Cleanup After Inference
- Heuristic:Scikit learn Scikit learn Working Memory Tuning
- Heuristic:Googleapis Python genai API Retry Backoff Strategy
- Heuristic:Turboderp org Exllamav2 Dynamic Generator Tuning
- Heuristic:Neuml Txtai Llama Cpp Context Fallback
- Heuristic:Alibaba MNN Weight Quantization Strategy
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:Mage ai Mage ai HTTP Request Timeout Defaults
Environments
- Environment:Lance format Lance Cloud Storage Credentials
- Environment:DataExpert io Data engineer handbook PostgreSQL Docker Environment
- Environment:Cypress io Cypress Browser Requirements
- Environment:SqueezeAILab ETS Evaluation Python Stack
- Environment:Anthropics Anthropic sdk python AWS Bedrock Environment
- Environment:Langgenius Dify Docker Compose Environment
- Environment:Lance format Lance SIMD And Platform Requirements
- Environment:Google deepmind Mujoco MJX JAX Environment
- Environment:Sktime Pytorch forecasting Matplotlib Plotting Dependencies
- Environment:Mage ai Mage ai Python 3 9 Runtime