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:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:TA Lib Ta lib python Streaming Indicator Computation
- Workflow:Farama Foundation Gymnasium Vectorized Environment Training
- Workflow:LaurentMazare Tch rs JIT Model Inference
- Workflow:Explodinggradients Ragas RAG Evaluation
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:Explodinggradients Ragas Agent Evaluation
- Workflow:Cohere ai Cohere python Streaming Chat
- Workflow:CrewAIInc CrewAI Knowledge RAG Pipeline
- Workflow:Marker Inc Korea AutoRAG Evaluation Data Creation
Principles
- Principle:Bitsandbytes foundation Bitsandbytes 4bit Quantization Lookup Tables
- Principle:Datajuicer Data juicer Operator Fusion
- Principle:Lm sys FastChat OpenAI Compatible API Serving
- Principle:ClickHouse ClickHouse Compile Time Reflection
- Principle:Deepseek ai Janus ODE Denoising
- Principle:ArroyoSystems Arroyo Failure Detection
- Principle:Langchain ai Langgraph Development Server
- Principle:AUTOMATIC1111 Stable diffusion webui UI Component Pattern
- Principle:Guardrails ai Guardrails Telemetry
- Principle:Dagster io Dagster Dbt Project Integration
Implementations
- Implementation:ARISE Initiative Robosuite PickPlace Environment
- Implementation:CrewAIInc CrewAI MCP Server Adapter
- Implementation:Kubeflow Kubeflow Manifests E2E Testing
- Implementation:Apache Paimon DataTypeDefaultVisitor
- Implementation:Mlc ai Mlc llm MLCEngine Generate
- Implementation:Ray project Ray PlacementGroupCreationOptions
- Implementation:Langfuse Langfuse Web Env Config
- Implementation:Haifengl Smile NearestNeighborGraph
- Implementation:Googleapis Python genai Interactions Streaming
- Implementation:Ray project Ray RayCallGenerator
Heuristics
- Heuristic:Deepseek ai Janus Bfloat16 Dtype Selection
- Heuristic:Open compass VLMEvalKit WORLD SIZE Unset For Model Building
- Heuristic:OpenBMB UltraFeedback Position Bias Mitigation
- Heuristic:Google deepmind Dm control Tolerance Reward Tuning
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
- Heuristic:Alibaba ROLL GPU Memory Offload Strategy
- Heuristic:Zai org CogVideo BF16 FP16 Precision Selection
- Heuristic:Google deepmind Dm control MJCF Model Composition Gotchas
- Heuristic:Wandb Weave Payload Size Limits
- Heuristic:Open compass VLMEvalKit Video Frame Sampling Configuration
Environments
- Environment:Fastai Fastbook Python FastAI Environment
- Environment:Ggml org Ggml Metal GPU Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:Mlc ai Web llm Chrome Extension Manifest V3
- Environment:Vespa engine Vespa CMake Cpp23 Build Environment
- Environment:Onnx Onnx Python Runtime Environment
- Environment:OpenRLHF OpenRLHF vLLM Environment
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:Sgl project Sglang Grafana
- Environment:Kornia Kornia PyTorch Python Environment