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:Turboderp org Exllamav2 Text Generation
- Workflow:Unstructured IO Unstructured Document Partitioning
- Workflow:Romsto Speculative Decoding Interactive CLI Comparison
- Workflow:Trailofbits Fickling PyTorch Format Identification
- Workflow:Openclaw Openclaw Channel Connection
- Workflow:Openai Openai node Realtime Conversation
- Workflow:Isaac sim IsaacGymEnvs Policy Inference and Evaluation
- Workflow:Alibaba ROLL Reward Flow Diffusion Pipeline
- Workflow:FMInference FlexLLMGen HELM Benchmark Evaluation
- Workflow:Cypress io Cypress Local Development Environment
Principles
- Principle:Tensorflow Serving Session Bundle Migration
- Principle:Datahub project Datahub Docker Prerequisites
- Principle:CARLA simulator Carla CMake Build Configuration
- Principle:PacktPublishing LLM Engineers Handbook Document Persistence
- Principle:Treeverse LakeFS GC Result Verification
- Principle:MarketSquare Robotframework browser Plugin Architecture
- Principle:SeleniumHQ Selenium PageFactory Initialization
- Principle:BerriAI Litellm Custom Logger Development
- Principle:Ggml org Llama cpp Speculative Generation
- Principle:Dagster io Dagster Project Scaffolding
Implementations
- Implementation:FlowiseAI Flowise CreateDocumentStore
- Implementation:Huggingface Datasets Nifti
- Implementation:FlowiseAI Flowise NvidiaNIMDialog
- Implementation:Mage ai Mage ai Tableau Client
- Implementation:Googleapis Python genai Part From Function Response
- Implementation:Ollama Ollama Llama Context
- Implementation:Online ml River TimeSeries Forecaster Base
- Implementation:Scikit learn Scikit learn Cross Validate
- Implementation:DataExpert io Data engineer handbook Log processing
- Implementation:Explodinggradients Ragas Evaluate Function
Heuristics
- Heuristic:Vllm project Vllm KV Cache Block Size Selection
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:Helicone Helicone Cost Precision Multiplier
- Heuristic:Cleanlab Cleanlab KNN Distance Metric Selection
- Heuristic:Microsoft Agent framework Async Context Manager Cleanup
- Heuristic:Wandb Weave Batch Processing Tuning
- Heuristic:CarperAI Trlx KL Coefficient Adaptation
- Heuristic:Princeton nlp Tree of thought llm Functools Partial Model Binding
- Heuristic:Tencent Ncnn Vulkan Pipeline Warmup
- Heuristic:Openai CLIP Class Name Curation
Environments
- Environment:Deepspeedai DeepSpeed CUDA GPU Environment
- Environment:VainF Torch Pruning PyTorch Python Core
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:NVIDIA TransformerEngine CUDA Toolkit Requirements
- Environment:PrefectHQ Prefect Python Runtime Environment
- Environment:ARISE Initiative Robomimic PyTorch CUDA Environment
- Environment:Isaac sim IsaacGymEnvs Python CUDA Runtime
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment
- Environment:Unslothai Unsloth CUDA BitsAndBytes
- Environment:Openai Openai node WebSocket Dependency