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:Axolotl ai cloud Axolotl Multimodal Vision Finetuning
- Workflow:Dotnet Machinelearning Time Series Forecasting
- Workflow:Volcengine Verl Multi Turn Tool Use Training
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:Infiniflow Ragflow Chat Application Setup
- Workflow:Tensorflow Serving REST API Inference
- Workflow:Mlc ai Mlc llm Model Compilation
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:Heibaiying BigData Notes Storm Topology Development
- Workflow:Apache Spark Building and Testing
Principles
- Principle:Sail sg LongSpec VLLM Inference Client
- Principle:Kornia Kornia Automatic Augmentation
- Principle:Bitsandbytes foundation Bitsandbytes CI CD Build Pipeline
- Principle:Sdv dev SDV Range Constraint
- Principle:Webdriverio Webdriverio CLI Architecture
- Principle:Online ml River API Documentation Generation
- Principle:OpenHands OpenHands Webhook Reception
- Principle:Huggingface Datatrove JSONL Data Writing
- Principle:Spotify Luigi Database Data Loading
- Principle:Google deepmind Dm control Environment Wrapping
Implementations
- Implementation:Lance format Lance Java Dataset
- Implementation:Predibase Lorax BGMV Expand Slice Kernel
- Implementation:Risingwavelabs Risingwave Deserializer Interface
- Implementation:Pyro ppl Pyro ProvenanceTensor
- Implementation:Turboderp org Exllamav2 ExLlamaV2PrefixFilter
- Implementation:Pytorch Serve Llama2 Generate
- Implementation:NVIDIA NeMo Curator CommonCrawl Downloader
- Implementation:Ollama Ollama Llama Grammar Types
- Implementation:NVIDIA NeMo Curator QuotationRemover
- Implementation:Vllm project Vllm CPU Attn Impl
Heuristics
- Heuristic:Microsoft Semantic kernel Prompt Injection Safety
- Heuristic:Bentoml BentoML Adaptive Batching Tuning
- Heuristic:Evidentlyai Evidently Drift Detection Thresholds
- Heuristic:Hiyouga LLaMA Factory CUDA Memory Optimization
- Heuristic:Speechbrain Speechbrain Nonfinite Loss Handling
- Heuristic:Gretelai Gretel synthetics Memory Chunking For Normalization
- Heuristic:Facebookresearch Audiocraft Audio Normalization Strategies
- Heuristic:Explodinggradients Ragas Deprecation Migration Guide
- Heuristic:Langgenius Dify Warning Deprecated Default Datasource Auth
- Heuristic:Cohere ai Cohere python Embed Auto Batching Strategy
Environments
- Environment:Pytorch Serve vLLM Engine Environment
- Environment:Speechbrain Speechbrain Speech Enhancement Dependencies
- Environment:Unstructured IO Unstructured OpenAI API
- Environment:Vllm project Vllm CUDA
- Environment:Langchain ai Langgraph Python Runtime Environment
- Environment:Norrrrrrr lyn WAInjectBench OpenAI API Credentials
- Environment:Nightwatchjs Nightwatch Android Mobile Testing
- Environment:CARLA simulator Carla Build From Source Requirements
- Environment:Kserve Kserve Gateway API
- Environment:Spotify Luigi Python Runtime