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:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:Hiyouga LLaMA Factory Full Parameter SFT
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
- Workflow:Teamcapybara Capybara Custom Selector Definition
- Workflow:CrewAIInc CrewAI Hierarchical Crew Execution
- Workflow:Dotnet Machinelearning Binary Classification Pipeline
- Workflow:Groq Groq python Audio Transcription
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Apache Flink File Sink Pipeline
- Workflow:Mlc ai Mlc llm Model Compilation
Principles
- Principle:Bitsandbytes foundation Bitsandbytes 4bit Quantization Lookup Tables
- Principle:Microsoft BIPIA Clean Response Collection
- Principle:AUTOMATIC1111 Stable diffusion webui Weight interpolation methods
- Principle:Togethercomputer Together python LLM Evaluation
- Principle:Huggingface Transformers Benchmark Model Loading
- Principle:Hiyouga LLaMA Factory Muon Optimization
- Principle:Interpretml Interpret Partial Dependence Explanation
- Principle:Togethercomputer Together python Message Construction
- Principle:PacktPublishing LLM Engineers Handbook Supervised Finetuning
- Principle:Shiyu coder Kronos Single Series Forecasting
Implementations
- Implementation:AUTOMATIC1111 Stable diffusion webui Train embedding
- Implementation:Huggingface Datasets Dataset Save To Disk
- Implementation:Heibaiying BigData Notes Maven Packaging for Storm
- Implementation:Evidentlyai Evidently Legacy Collector Storage
- Implementation:Kornia Kornia Bilateral Filter
- Implementation:NVIDIA NeMo Curator Wikipedia Extractor
- Implementation:Microsoft Playwright BrowserServerLauncher
- Implementation:BerriAI Litellm Prompt Caching Cache
- Implementation:NVIDIA NeMo Curator FuzzyDeduplicationWorkflow
- Implementation:Huggingface Optimum RunConfig
Heuristics
- Heuristic:Princeton nlp SimPO Multi Seed Diversity
- Heuristic:Hpcaitech ColossalAI CUDA Device Max Connections Tip
- Heuristic:Volcengine Verl Sequence Length Balancing
- Heuristic:Microsoft Playwright Browser Specific Workarounds
- Heuristic:Vllm project Vllm Batch Size Hardware Scaling
- Heuristic:Huggingface Peft LoRA Default Configuration
- Heuristic:Facebookresearch Audiocraft Chroma Conditioning Cache Requirement
- Heuristic:Mlc ai Web llm Grammar Matcher Reuse
- Heuristic:Anthropics Anthropic sdk python Retry Backoff Strategy
- Heuristic:LLMBook zh LLMBook zh github io BF16 Mixed Precision Default
Environments
- Environment:AUTOMATIC1111 Stable diffusion webui Python And PyTorch Runtime
- Environment:Norrrrrrr lyn WAInjectBench Conda Python 39 CUDA Environment
- Environment:Langgenius Dify Credentials And Env Vars
- Environment:Datahub project Datahub Python 3 10 Ingestion Environment
- Environment:BerriAI Litellm Redis Cache Backend
- Environment:Bentoml BentoML Python Runtime
- Environment:Vespa engine Vespa Java 17 Build Runtime
- Environment:SeldonIO Seldon core Docker Compose Local Environment
- Environment:Open compass VLMEvalKit GPU CUDA Environment
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment