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:Avhz RustQuant Analytic Option Pricing
- Workflow:Hiyouga LLaMA Factory PPO RLHF Training
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Deepset ai Haystack RAG Evaluation Pipeline
- Workflow:Anthropics Anthropic sdk python Tool Use Integration
- Workflow:Huggingface Trl GRPO Training
- Workflow:Cypress io Cypress CI Pipeline Integration
- Workflow:Neuml Txtai API Deployment
- Workflow:Guardrails ai Guardrails Structured Data Generation
- Workflow:Huggingface Open r1 SFT Distillation
Principles
- Principle:Anthropics Anthropic sdk python Thinking Configuration
- Principle:Treeverse LakeFS Import Source Preparation
- Principle:FlagOpen FlagEmbedding Finetuned Reranker Validation
- Principle:ClickHouse ClickHouse TCP Server Startup
- Principle:Puppeteer Puppeteer Web Worker Interaction
- Principle:Tensorflow Serving Thread Pool Management
- Principle:Tensorflow Serving Session Safety
- Principle:Deepset ai Haystack Optional Dependency Handling
- Principle:Risingwavelabs Risingwave Iceberg Integration
- Principle:Apache Shardingsphere Configuration Change Initiation
Implementations
- Implementation:Trailofbits Fickling AnalysisResults Severity
- Implementation:Pytorch Serve VLLMHandler
- Implementation:Sktime Pytorch forecasting GroupNormalizer
- Implementation:Vllm project Vllm Broadcast Load Epilogue Array C3X
- Implementation:Run llama Llama index PromptMixin
- Implementation:Astronomer Astronomer cosmos SnowflakeUserPasswordProfileMapping
- Implementation:Sktime Pytorch forecasting Show Versions
- Implementation:Vibrantlabsai Ragas StringMetrics
- Implementation:NVIDIA NeMo Curator ShuffleStage
- Implementation:Ggml org Ggml Gpt2 eval
Heuristics
- Heuristic:Turboderp org Exllamav2 Memory Optimization Techniques
- Heuristic:Alibaba MNN NC4HW4 Data Layout
- Heuristic:Openai CLIP Class Name Curation
- Heuristic:Cleanlab Cleanlab KNN Distance Metric Selection
- Heuristic:Allenai Open instruct Warning Archived Dev Scripts
- Heuristic:Cohere ai Cohere python ToolCallV2 Auto UUID Override
- Heuristic:Getgauge Taiko Implicit Wait Tuning
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:Teamcapybara Capybara Async Waiting And Retry
- Heuristic:Helicone Helicone Anthropic Cache Double Count Prevention
Environments
- Environment:Unslothai Unsloth CUDA VLLM
- Environment:BerriAI Litellm Python Runtime
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:Treeverse LakeFS S3 Gateway Test Environment
- Environment:Huggingface Trl Quantization Environment
- Environment:Ggml org Llama cpp Python Conversion Environment
- Environment:Nautechsystems Nautilus trader Asyncio Uvloop Event Loop
- Environment:Bitsandbytes foundation Bitsandbytes HPU Gaudi Runtime
- Environment:Hiyouga LLaMA Factory Quantization Dependencies
- Environment:NVIDIA TransformerEngine GPU Compute Capability