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:Confident ai Deepeval Synthetic Dataset Generation
- Workflow:Avhz RustQuant Model Calibration
- Workflow:Mlc ai Web llm Function Calling
- Workflow:FlagOpen FlagEmbedding Embedder Inference
- Workflow:Apache Paimon Distributed Processing With Ray
- Workflow:Fastai Fastbook Neural Network From Scratch
- Workflow:Intel Ipex llm vLLM Serving
- Workflow:Promptfoo Promptfoo Custom Provider Integration
- Workflow:TobikoData Sqlmesh Model development and testing
- Workflow:Lm sys FastChat MT Bench Evaluation
Principles
- Principle:Vllm project Vllm API Server Deployment
- Principle:Neuml Txtai Keyword Scoring
- Principle:Huggingface Datasets Archive Extraction
- Principle:Webdriverio Webdriverio CommandRegistration
- Principle:AUTOMATIC1111 Stable diffusion webui Noise addition and guided denoising
- Principle:Pyro ppl Pyro Capture Recapture
- Principle:Huggingface Datatrove Multilingual Word Tokenization
- Principle:Microsoft Semantic kernel CopilotAgent Plugin OpenAPI Specs
- Principle:Apache Hudi Clustering Execution
- Principle:Mlflow Mlflow Code Quality Linting
Implementations
- Implementation:Neuml Txtai RAG Call
- Implementation:Risingwavelabs Risingwave DbzChangeEventConsumer
- Implementation:Elevenlabs Elevenlabs python ClientToolConfigOutput
- Implementation:CARLA simulator Carla Client Replay File
- Implementation:Google deepmind Mujoco Engine Vis Interact
- Implementation:Microsoft Semantic kernel ContactsPlugin OpenAPI
- Implementation:BerriAI Litellm Endpoint Factory
- Implementation:Arize ai Phoenix Datasets Create Dataset
- Implementation:Kserve Kserve LLM Inference Scheduler
- Implementation:Mit han lab Llm awq LMEvalAdaptor
Heuristics
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
- Heuristic:OpenGVLab InternVL LoRA Alpha Scaling
- Heuristic:SeldonIO Seldon core Model Scheduling Preference Tip
- Heuristic:Alibaba MNN Memory Mode Selection
- Heuristic:Predibase Lorax CUDA Graph Batch Size Caching
- Heuristic:Run llama Llama index Embedding Batch Size Tuning
- Heuristic:SeleniumHQ Selenium Warning Deprecated Proxy FTP Methods
- Heuristic:LaurentMazare Tch rs CuDNN Benchmark Mode
- Heuristic:Rapidsai Cuml Dask Data Partitioning
- Heuristic:Google deepmind Dm control MJCF Model Composition Gotchas
Environments
- Environment:LLMBook zh LLMBook zh github io HuggingFace Transformers Stack
- Environment:ArroyoSystems Arroyo Rust Runtime
- Environment:Openai CLIP Python Dependencies
- Environment:DevExpress Testcafe Firefox Marionette
- Environment:Protectai Llm guard Python Runtime Dependencies
- Environment:Sgl project Sglang CUDA
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Apache Shardingsphere Java Runtime Environment
- Environment:Duckdb Duckdb CMake Build Toolchain
- Environment:AnswerDotAI RAGatouille GPU CUDA Runtime