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:Cohere ai Cohere python Model Finetuning
- Workflow:Microsoft Autogen Tool Augmented Agent
- Workflow:Iterative Dvc Pipeline Reproduction
- Workflow:EvolvingLMMs Lab Lmms eval Server Mode Evaluation
- Workflow:Langchain ai Langgraph CLI Deployment
- Workflow:FlowiseAI Flowise Chatflow Creation
- Workflow:Tencent Ncnn Image Classification Inference
- Workflow:Apache Druid Streaming Ingestion Management
- Workflow:Haotian liu LLaVA Single Image Inference
- Workflow:Cypress io Cypress Local Development Environment
Principles
- Principle:Marker Inc Korea AutoRAG Quality Filtering
- Principle:Ollama Ollama Token Sampling
- Principle:Guardrails ai Guardrails RailSpecification
- Principle:Langgenius Dify Variable Wiring
- Principle:Apache Shardingsphere Cluster Repository Initialization
- Principle:Guardrails ai Guardrails Server Config Scaffolding
- Principle:Ggml org Ggml Vision Encoder Execution
- Principle:Intel Ipex llm Embedding And Vector Store
- Principle:Openai Whisper Language Detection
- Principle:Pyro ppl Pyro MCMC Posterior Sampling
Implementations
- Implementation:Huggingface Datasets JaxFormatter
- Implementation:SeleniumHQ Selenium Closure Asserts
- Implementation:Tencent Ncnn Pnnx Export
- Implementation:Sgl project Sglang KVCache IO
- Implementation:Apache Flink IteratorResultIterator
- Implementation:OWASP Www project top 10 for large language model applications ReportTemplate Render
- Implementation:Kserve Kserve InferenceGraph Full CRD
- Implementation:Microsoft Playwright Utils Bundle Package Lock
- Implementation:Apache Hudi CompactionCommitSink Invoke
- Implementation:Ggml org Llama cpp Convert LoRA To GGUF
Heuristics
- Heuristic:Hpcaitech ColossalAI Flash Attention Dtype Restriction
- Heuristic:OpenRLHF OpenRLHF Packing Samples Efficiency Tip
- Heuristic:Langgenius Dify Celery Queue Separation
- Heuristic:Webdriverio Webdriverio Default Timeout Configuration
- Heuristic:Kornia Kornia Morphology Engine Selection
- Heuristic:Huggingface Peft LoRA Initialization Strategy Selection
- Heuristic:Risingwavelabs Risingwave Stream Chunk Sizing
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:NVIDIA NeMo Aligner PPO NCCL Algorithm Setting
- Heuristic:Openai Whisper Temperature Fallback Strategy
Environments
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:Bitsandbytes foundation Bitsandbytes XPU SYCL Runtime
- Environment:Interpretml Interpret Visualization Environment
- Environment:Truera Trulens Streamlit Dashboard Environment
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:FMInference FlexLLMGen CUDA GPU
- Environment:OpenRLHF OpenRLHF Flash Attention Environment
- Environment:Apache Airflow Development Contributor Environment
- Environment:Fastai Fastbook NLP SpaCy Environment
- Environment:Dotnet Machinelearning TorchSharp Environment