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:Speechbrain Speechbrain Speech Enhancement Training
- Workflow:Facebookresearch Audiocraft MusicGen Text To Music Inference
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Lucidrains X transformers Encoder Decoder Sequence to Sequence
- Workflow:Apache Shardingsphere Shadow Rule Configuration
- Workflow:EvolvingLMMs Lab Lmms eval Custom Model Integration
- Workflow:SeleniumHQ Selenium Contributor Development Workflow
- Workflow:Mlc ai Web llm Text Embeddings And RAG
- Workflow:Kubeflow Pipelines XGBoost Training Pipeline
- Workflow:Nightwatchjs Nightwatch Programmatic API Usage
Principles
- Principle:Protectai Llm guard Sentiment Analysis
- Principle:Ollama Ollama GGUF Model Conversion Gemma3
- Principle:OpenGVLab InternVL LLaVA Multimodal Architecture
- Principle:Dagster io Dagster Materialization Metadata
- Principle:Romsto Speculative Decoding Logits Processing
- Principle:Pytorch Serve Documentation Generation
- Principle:Sdv dev SDV Diagnostic Reporting
- Principle:Testtimescaling Testtimescaling github io Taxonomy Classification
- Principle:Apache Shardingsphere SQL Statement Interception
- Principle:Langgenius Dify Workflow Publishing
Implementations
- Implementation:Neuml Txtai Console
- Implementation:Interpretml Interpret LogLossBinaryObjective
- Implementation:Openai Openai python BaseModel Validation
- Implementation:OpenGVLab InternVL MPT Model
- Implementation:ArroyoSystems Arroyo Avro Schema Converter
- Implementation:Astronomer Astronomer cosmos ClickhouseUserPasswordProfileMapping
- Implementation:Mlc ai Mlc llm Phi Templates
- Implementation:FlagOpen FlagEmbedding BGE Finetune Modeling
- Implementation:Teamcapybara Capybara Spec Has Select
- Implementation:NVIDIA NeMo Curator ImageFilterBase
Heuristics
- Heuristic:Huggingface Transformers Gradient Checkpointing Memory Tradeoff
- Heuristic:OpenBMB UltraFeedback Score Parsing Robustness
- Heuristic:Avdvg InjectGuard Module Level Initialization
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
- Heuristic:Eric mitchell Direct preference optimization Activation Checkpointing Memory
- Heuristic:Dagster io Dagster Batch Size Tuning
- Heuristic:Scikit learn Scikit learn Data Leakage Prevention
- Heuristic:Mlc ai Web llm KV Cache Window Configuration
- Heuristic:Snorkel team Snorkel Minimum Three LFs
- Heuristic:LLMBook zh LLMBook zh github io IGNORE INDEX Loss Masking
Environments
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Google deepmind Mujoco C Build Environment
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Huggingface Diffusers Quantization Environment
- Environment:Ollama Ollama CGo Runtime
- Environment:Lakeraai Pint benchmark Python 310 With Pandas
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Risingwavelabs Risingwave Docker Deployment Environment
- Environment:Sktime Pytorch forecasting Matplotlib Plotting Dependencies
- Environment:Guardrails ai Guardrails Python 3 10 Runtime