Main Page
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:Truera Trulens RAG Evaluation With LangChain
- Workflow:Wandb Weave Tracing Setup
- Workflow:Axolotl ai cloud Axolotl DPO Preference Alignment
- Workflow:Google deepmind Dm control Control Suite RL Training
- Workflow:Apache Kafka Docker Image Release
- Workflow:Huggingface Transformers PEFT Adapter Integration
- Workflow:Truera Trulens Custom App Instrumentation And Evaluation
- Workflow:MaterializeInc Materialize CI Pipeline Generation
- Workflow:Apache Flink Stream File Compaction
- Workflow:ThreeSR Awesome Inference Time Scaling Automated Paper Addition
Principles
- Principle:Anthropics Anthropic sdk python Provider Client Initialization
- Principle:OpenGVLab InternVL Weight Format Conversion
- Principle:Huggingface Trl Reward Model Training
- Principle:Diagram of thought Diagram of thought Problem Formulation
- Principle:Guardrails ai Guardrails Guard Validator Composition
- Principle:Alibaba ROLL DPO Worker Initialization
- Principle:Unstructured IO Unstructured Section Aware Chunking
- Principle:Fede1024 Rust rdkafka Mock Client Configuration
- Principle:OpenGVLab InternVL Query Based Vision Language Bridge
- Principle:Dagster io Dagster Custom Resource Pattern
Implementations
- Implementation:Microsoft Playwright NetworkDispatchers
- Implementation:CrewAIInc CrewAI Stagehand Tool
- Implementation:Axolotl ai cloud Axolotl ModelLoader Load Multimodal
- Implementation:Puppeteer Puppeteer ResolveBuildId
- Implementation:Langchain ai Langgraph Add Messages
- Implementation:Explodinggradients Ragas Collections RougeScore Metric
- Implementation:Truera Trulens Record Viewer Utils
- Implementation:Tensorflow Serving Docker Build Serving Image
- Implementation:Openai Openai node Evals Resource
- Implementation:Apache Druid Aggregate Macro
Heuristics
- Heuristic:Sgl project Sglang Attention Backend Selection
- Heuristic:Tencent Ncnn Optimize Before Quantize
- Heuristic:Romsto Speculative Decoding Gamma Tuning
- Heuristic:Langgenius Dify Extension Initialization Order
- Heuristic:Isaac sim IsaacGymEnvs JIT Profiling Optimization
- Heuristic:Huggingface Alignment handbook QLoRA Learning Rate Scaling
- Heuristic:Datahub project Datahub Emitter Selection Strategy
- Heuristic:Huggingface Transformers FSDP Activation Checkpointing Tip
- Heuristic:LMCache LMCache Chunk Size And Default Config
- Heuristic:Datajuicer Data juicer Operator Fusion Rules
Environments
- Environment:Facebookresearch Habitat lab Python 3 9 Core Dependencies
- Environment:Vespa engine Vespa Docker OCI Container Runtime
- Environment:Haosulab ManiSkill Python SAPIEN Core
- Environment:ARISE Initiative Robomimic HuggingFace Hub Dependencies
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Trailofbits Fickling Python Runtime
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:Openai Whisper FFmpeg
- Environment:Openai Whisper Triton
- Environment:Apache Dolphinscheduler Netty Runtime