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:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Vllm project Vllm Speculative Decoding
- Workflow:Webdriverio Webdriverio WDIO Testrunner Setup
- Workflow:SeleniumHQ Selenium Contributor Development Workflow
- Workflow:SeleniumHQ Selenium Chrome DevTools Protocol Integration
- Workflow:Mlc ai Web llm Function Calling
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:TA Lib Ta lib python Streaming Indicator Computation
- Workflow:Spcl Graph of thoughts Custom GoT Use Case Integration
- Workflow:Unstructured IO Unstructured Performance Profiling
Principles
- Principle:Sgl project Sglang OpenAI Client Configuration
- Principle:Run llama Llama index Agent Output Processing
- Principle:Langfuse Langfuse Event Validation and Schema Parsing
- Principle:Langchain ai Langgraph Language Model Configuration
- Principle:Openclaw Openclaw Reply Delivery
- Principle:VainF Torch Pruning Taylor Importance
- Principle:Haosulab ManiSkill LeRobot Format Export
- Principle:Datahub project Datahub Client Authentication
- Principle:AUTOMATIC1111 Stable diffusion webui Textual inversion training loop
- Principle:Avhz RustQuant Mathematical Sequences
Implementations
- Implementation:Run llama Llama index LLM Utils
- Implementation:OpenHands OpenHands Summarize Issue Solvability
- Implementation:NVIDIA DALI Fn Readers Video
- Implementation:Princeton nlp Tree of thought llm Get Task
- Implementation:Apache Beam InMemoryJobService Run
- Implementation:Interpretml Interpret RandomDeterministic
- Implementation:Ggml org Llama cpp LoRA Merge Ctx
- Implementation:Puppeteer Puppeteer Disposable
- Implementation:TA Lib Ta lib python Stream Wrapper Integration
- Implementation:NVIDIA TransformerEngine Ops BasicLinear
Heuristics
- Heuristic:Danijar Dreamerv3 Adaptive Gradient Clipping
- Heuristic:Run llama Llama index Worker Count Configuration
- Heuristic:Cypress io Cypress Global Install Warning
- Heuristic:Allenai Open instruct Logprob Clamping
- Heuristic:Intel Ipex llm DeepSpeed Tensor Parallel Tips
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Image Size Multiple of Four
- Heuristic:BerriAI Litellm Retry Backoff Strategy
- Heuristic:Gretelai Gretel synthetics Gumbel Softmax NaN Retry
- Heuristic:Confident ai Deepeval Timeout and Retry Tuning
- Heuristic:Cypress io Cypress V8 Snapshot Memory
Environments
- Environment:Online ml River Python Runtime Environment
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:Bentoml BentoML Triton Inference Server
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Vllm project Vllm Benchmarks
- Environment:Sgl project Sglang OpenAI
- Environment:Langchain ai Langchain Anthropic API Credentials
- Environment:Microsoft Onnxruntime CUDA GPU Environment