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:Triton inference server Server Custom Container Build
- Workflow:Groq Groq python Chat Completion
- Workflow:PacktPublishing LLM Engineers Handbook Feature Engineering
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Apache Paimon Blob Storage With Descriptors
- Workflow:Langfuse Langfuse Evaluation pipeline
- Workflow:Teamcapybara Capybara RSpec Integration Setup
- Workflow:Mlc ai Web llm Function Calling
- Workflow:Webdriverio Webdriverio Standalone Browser Automation
- Workflow:ContextualAI HALOs Reward Model Training
Principles
- Principle:OpenHands OpenHands Nested Conversation Creation
- Principle:Guardrails ai Guardrails Stream Result Handling
- Principle:Openclaw Openclaw Channel Health Verification
- Principle:Danijar Dreamerv3 Agent Initialization
- Principle:Pola rs Polars SQL Data Registration
- Principle:HKUDS AI Trader Performance Visualization
- Principle:Deepset ai Haystack Metadata Based Routing
- Principle:Apache Beam Execution Driving
- Principle:TA Lib Ta lib python OHLC Data Preparation
- Principle:SeldonIO Seldon core Monitoring Pipeline Validation
Implementations
- Implementation:AUTOMATIC1111 Stable diffusion webui UniPC Sampler
- Implementation:Huggingface Datasets Dataset Sort
- Implementation:Deepspeedai DeepSpeed PipelineEngine Train Batch
- Implementation:Google deepmind Dm control Reference Pose Rewards
- Implementation:CrewAIInc CrewAI BrightData SERP Tool
- Implementation:Arize ai Phoenix Legacy LiteLLMModel
- Implementation:Ggml org Llama cpp GGUF Split
- Implementation:Online ml River Facto FM
- Implementation:Apache Flink SourceReaderOptions
- Implementation:NVIDIA TransformerEngine TE LayerNorm
Heuristics
- Heuristic:Princeton nlp Tree of thought llm Ad Hoc Value Map Scoring
- Heuristic:Alibaba ROLL Sequence Packing Alignment
- Heuristic:Guardrails ai Guardrails RAIL Argument Parsing Security
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Openai Whisper Log Probability Threshold
- Heuristic:Princeton nlp SimPO Hyperparameter Tuning
- Heuristic:Sdv dev SDV CTGAN Column Performance
- Heuristic:Langchain ai Langchain Pydantic V2 Configuration Tips
- Heuristic:Recommenders team Recommenders Test Timing Budgets
- Heuristic:Openclaw Openclaw Warning Suppression For Known Deprecations
Environments
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:Mbzuai oryx Awesome LLM Post training Python Requests
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment
- Environment:Alibaba MNN CPU Build Environment
- Environment:Princeton nlp SimPO VLLM Inference
- Environment:FMInference FlexLLMGen HuggingFace Access
- Environment:CARLA simulator Carla Build From Source Requirements
- Environment:Vllm project Vllm CUDA Runtime
- Environment:Evidentlyai Evidently Python Core Environment