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:Mistralai Client python Text Embeddings
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:DataExpert io Data engineer handbook AB Experimentation Server
- Workflow:MarketSquare Robotframework browser Plugin Development
- Workflow:LLMBook zh LLMBook zh github io Data Preprocessing Pipeline
- Workflow:Openai Openai agents python Tool Integrated Agent
- Workflow:Deepset ai Haystack Extractive QA Pipeline
- Workflow:Huggingface Transformers Model Quantization
- Workflow:Zai org CogVideo Diffusers Image to Video Inference
- Workflow:Diagram of thought Diagram of thought DoT Prompt Customization
Principles
- Principle:Huggingface Datasets Framework Tensor Conversion
- Principle:AUTOMATIC1111 Stable diffusion webui Model Loading
- Principle:Mlflow Mlflow Container Orchestration
- Principle:Huggingface Datatrove Pipeline Statistics Tracking
- Principle:Mbzuai oryx Awesome LLM Post training Keyword Data Loading
- Principle:Triton inference server Server Inference Request
- Principle:Kserve Kserve Serving Runtime Configuration
- Principle:Google deepmind Mujoco CPU Model Loading
- Principle:Online ml River Iterative Progressive Validation
- Principle:Sail sg LongSpec Prompt Formatting
Implementations
- Implementation:BerriAI Litellm Agent Types
- Implementation:Triton inference server Server L0 Grpc Test
- Implementation:Kornia Kornia Quaternion
- Implementation:Kserve Kserve LocalModelNode Agent DaemonSet
- Implementation:Openai Openai node Audio Resource
- Implementation:Rapidsai Cuml PCA UMAP TSNE Configuration
- Implementation:FMInference FlexLLMGen DeepSpeed Runtime Utils
- Implementation:Tensorflow Serving ServerCore Create And ReloadConfig
- Implementation:Ggml org Ggml Internal utilities
- Implementation:Microsoft Agent framework Edge Condition Function Pattern
Heuristics
- Heuristic:Mlc ai Mlc llm BLAS Dispatch Decision
- Heuristic:Roboflow Rf detr Resolution Divisibility Rule
- Heuristic:Guardrails ai Guardrails Guard History Memory Management
- Heuristic:Openclaw Openclaw Conservative Error Retry Classification
- Heuristic:Bitsandbytes foundation Bitsandbytes Outlier Threshold Detection
- Heuristic:Predibase Lorax Flash Attention Backend Selection
- Heuristic:Avdvg InjectGuard Dataset Coverage Recall Bound
- Heuristic:Ggml org Ggml Quantization Type Selection
- Heuristic:Danijar Dreamerv3 Replay Context Carry Init
- Heuristic:Mlfoundations Open flamingo FSDP Manual Wrapping For Mixed Parameters
Environments
- Environment:Sgl project Sglang Multi Platform Accelerators
- Environment:Sktime Pytorch forecasting Matplotlib Plotting Dependencies
- Environment:EvolvingLMMs Lab Lmms eval Python Runtime Environment
- Environment:Tensorflow Serving Docker Runtime Environment
- Environment:Alibaba ROLL ROCm GPU Environment
- Environment:CarperAI Trlx Python Accelerate
- Environment:CrewAIInc CrewAI Python Runtime Environment
- Environment:Dotnet Machinelearning Platform Architecture Support
- Environment:Kserve Kserve Gateway API
- Environment:Langgenius Dify Node Frontend Environment