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:Mit han lab Llm awq TinyChat LLM Deployment
- Workflow:Bentoml BentoML Bento Build And Containerization
- Workflow:Openai Whisper Language Detection And Decoding
- Workflow:Neuml Txtai API Deployment
- Workflow:MaterializeInc Materialize Upgrade Testing
- Workflow:Langgenius Dify Visual Workflow Builder
- Workflow:NVIDIA NeMo Curator Text Curation Pipeline
- Workflow:Apache Airflow Scheduler Operation and Task Execution
- Workflow:Mage ai Mage ai Building a New Source Connector
- Workflow:Astronomer Astronomer cosmos Kubernetes dbt execution
Principles
- Principle:Volcengine Verl Rollout Generation
- Principle:Ollama Ollama Prompt Construction
- Principle:Allenai Open instruct Distributed Data Loading
- Principle:Diagram of thought Diagram of thought Raw Output Collection
- Principle:Mage ai Mage ai Catalog Selection
- Principle:Apache Druid Source Type Selection
- Principle:Langgenius Dify React Context Pattern
- Principle:Pyro ppl Pyro Neural Module Registration
- Principle:Scikit learn contrib Imbalanced learn Condensed Nearest Neighbour
- Principle:CrewAIInc CrewAI Crew Integration In Flow
Implementations
- Implementation:FlowiseAI Flowise OnConnect
- Implementation:Microsoft Semantic kernel CloudEvents GenerateDocumentsChat
- Implementation:Deepspeedai DeepSpeed XPU Adagrad
- Implementation:Openai Openai python Compacted Response
- Implementation:Google deepmind Dm control Randomizers
- Implementation:Open compass VLMEvalKit VisualGLM
- Implementation:Openai Openai python Response Incomplete Event
- Implementation:Kornia Kornia CLAHE
- Implementation:Datajuicer Data juicer RemoveWordsWithIncorrectSubstringsMapper
- Implementation:Avhz RustQuant CIR Bond Pricing
Heuristics
- Heuristic:ContextualAI HALOs Batch Size Divisibility
- Heuristic:Facebookresearch Habitat lab Warning Deprecated Legacy UI System
- Heuristic:Groq Groq python Retry Backoff Strategy
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Liu00222 Open Prompt Injection BPE Retokenization Parameters
- Heuristic:Gretelai Gretel synthetics Parallel Generation CUDA Disable
- Heuristic:Heibaiying BigData Notes Kafka Consumer Offset Strategy Tip
- Heuristic:Wandb Weave Batch Processing Tuning
- Heuristic:Microsoft Onnxruntime Memory Recomputation Optimization
- Heuristic:Cleanlab Cleanlab Confident Threshold Heuristic
Environments
- Environment:Run llama Llama index Sentence Transformers Finetuning
- Environment:Infiniflow Ragflow Python Runtime
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Microsoft DeepSpeedExamples VisualChat Training Environment
- Environment:Huggingface Peft BitsAndBytes Quantization
- Environment:Apache Dolphinscheduler Node Pnpm Runtime
- Environment:Datajuicer Data juicer GPU CUDA Environment
- Environment:Microsoft BIPIA Python CUDA GPU Environment
- Environment:Microsoft LoRA NLG Eval External Tools
- Environment:Pyro ppl Pyro Python PyTorch Core