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:Ggml org Llama cpp Multimodal Inference
- Workflow:Trailofbits Fickling Safe ML Model Loading
- Workflow:Huggingface Transformers Model Training With Trainer
- Workflow:Norrrrrrr lyn WAInjectBench Text Prompt Injection Detection
- Workflow:CARLA simulator Carla Simulation Recording and Replay
- Workflow:Mbzuai oryx Awesome LLM Post training Deep Paper Collection
- Workflow:DataTalksClub Data engineering zoomcamp Kafka Stream Processing
- Workflow:Run llama Llama index OpenAI LLM Finetuning
- Workflow:NVIDIA NeMo Curator Image Curation Pipeline
- Workflow:Farama Foundation Gymnasium Agent Evaluation Recording
Principles
- Principle:Lm sys FastChat Pairwise Rating Computation
- Principle:BerriAI Litellm Cache Initialization
- Principle:Explodinggradients Ragas DSPy Prompt Optimization
- Principle:Langgenius Dify Plugin Discovery
- Principle:Microsoft Playwright Configure Recording Context
- Principle:TobikoData Sqlmesh Dbt Model Discovery And Mapping
- Principle:ThreeSR Awesome Inference Time Scaling Git Automation
- Principle:Turboderp org Exllamav2 Bit Allocation Optimization
- Principle:Tensorflow Serving Kubernetes Cluster Creation
- Principle:Unstructured IO Unstructured Continuous Integration
Implementations
- Implementation:SeleniumHQ Selenium Point
- Implementation:Apache Druid ExpressionEditorDialog
- Implementation:Vllm project Vllm LLM Generate Speculative
- Implementation:Rapidsai Cuml Breast Cancer Dataset
- Implementation:Helicone Helicone Unified Types
- Implementation:Apache Druid NestedColumnDialog
- Implementation:Openai Openai node RunnableFunction
- Implementation:NVIDIA TransformerEngine TE RMSNorm
- Implementation:Datahub project Datahub Mce Diff Script
- Implementation:Neuml Txtai Topics
Heuristics
- Heuristic:Facebookresearch Habitat lab Mini Batch Environment Divisibility
- Heuristic:Haotian liu LLaVA Use Cache Training Inference Toggle
- Heuristic:Mlc ai Mlc llm Engine Mode Selection
- Heuristic:Mbzuai oryx Awesome LLM Post training Depth Limit Recursion At 2
- Heuristic:Explodinggradients Ragas Concurrency And Rate Limiting
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:Ollama Ollama Download Retry Strategy
- Heuristic:Arize ai Phoenix Notebook Event Loop Patching
- Heuristic:Apache Airflow Task Dependency Isolation
- Heuristic:Groq Groq python Error Handling Hierarchy
Environments
- Environment:Ucbepic Docetl Python Runtime
- Environment:Huggingface Datatrove Python Runtime
- Environment:CARLA simulator Carla Simulation Runtime
- Environment:Astronomer Astronomer cosmos Cloud Provider Dependencies
- Environment:DataTalksClub Data engineering zoomcamp Kestra Orchestration Environment
- Environment:Alibaba MNN Python Export Environment
- Environment:Hiyouga LLaMA Factory FP8 Training Environment
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:Allenai Open instruct CUDA GPU Training