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:Mlc ai Mlc llm Model Compilation
- Workflow:Neuml Txtai Semantic Search
- Workflow:Datahub project Datahub Java SDK V2 Entity Management
- Workflow:Lance format Lance Dataset Lifecycle
- Workflow:Openai Openai agents python Streaming Agent Execution
- Workflow:VainF Torch Pruning LLM Structural Pruning
- Workflow:Pola rs Polars SQL Query Interface
- Workflow:Romsto Speculative Decoding Speculative Decoding Inference
- Workflow:Onnx Onnx Model Validation
- Workflow:ClickHouse ClickHouse Packaging For Distribution
Principles
- Principle:DataExpert io Data engineer handbook Experiment User Assignment
- Principle:VainF Torch Pruning Growing Regularization
- Principle:Apache Spark SQL Documentation Generation
- Principle:Openai Openai node Fine Tuning Job Creation
- Principle:Nautechsystems Nautilus trader Cargo Manifest Conventions
- Principle:ClickHouse ClickHouse Fast Integer Formatting
- Principle:Cohere ai Cohere python Client Initialization
- Principle:Scikit learn Scikit learn Parameter Space Definition
- Principle:Haifengl Smile Point Data Preparation
- Principle:AUTOMATIC1111 Stable diffusion webui LDSR Upscaler
Implementations
- Implementation:Openai Openai python Realtime Connect
- Implementation:Ucbepic Docetl Directive MapResolveToMapWithCategories
- Implementation:Vllm project Vllm Vllm Serve CLI
- Implementation:Langchain ai Langchain ExaSearchRetriever
- Implementation:Spotify Luigi RemoteScheduler Worker
- Implementation:Microsoft Autogen Studio MCP Client
- Implementation:OpenGVLab InternVL Classification Config
- Implementation:Princeton nlp Tree of thought llm Naive Solve
- Implementation:Mlc ai Web llm Function Calling Model Ids
- Implementation:Tensorflow Serving Http Rest Api Handler Test
Heuristics
- Heuristic:NVIDIA TransformerEngine FP8 Recipe Auto Selection
- Heuristic:Webdriverio Webdriverio Stale Element Auto Refetch
- Heuristic:Langchain ai Langgraph Recursion Limit Tuning
- Heuristic:MarketSquare Robotframework browser GRPC Response Chunking
- Heuristic:FlagOpen FlagEmbedding Same Dataset Batching Tip
- Heuristic:Mlflow Mlflow Prompt Cache Tuning
- Heuristic:Microsoft Semantic kernel Experimental Feature Opt In
- Heuristic:DistrictDataLabs Yellowbrick Model Fitted State Detection
- Heuristic:NVIDIA TransformerEngine FP8 Checkpoint Compatibility
- Heuristic:Run llama Llama index Finetuning Warmup Steps
Environments
- Environment:Lucidrains X transformers Python Environment
- Environment:Iterative Dvc Python Runtime
- Environment:Unslothai Unsloth Llama Cpp
- Environment:Vllm project Vllm AMD ROCm
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:Ucbepic Docetl Docker Deployment
- Environment:Helicone Helicone Docker Compose Infrastructure
- Environment:Bentoml BentoML BentoCloud Credentials
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:Huggingface Alignment handbook Evaluation Tools