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:Trailofbits Fickling Safe ML Model Loading
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:Deepspeedai DeepSpeed Inference Engine Optimization
- Workflow:Astronomer Astronomer cosmos TaskGroup dbt integration
- Workflow:Spotify Luigi Local Batch Pipeline
- Workflow:Apache Druid Visual Data Exploration
- Workflow:Microsoft Agent framework Declarative Agent Definition
- Workflow:Huggingface Datatrove Dataset Tokenization
- Workflow:Mlfoundations Open flamingo Model Creation And Inference
- Workflow:Microsoft Agent framework Graph Based Workflow Execution
Principles
- Principle:Axolotl ai cloud Axolotl Continuous Integration Testing
- Principle:Langgenius Dify Embedding and Indexing
- Principle:Nightwatchjs Nightwatch Project Initialization
- Principle:Microsoft Autogen Tool Event Processing
- Principle:Huggingface Datasets JSON Export
- Principle:Nightwatchjs Nightwatch Client Configuration
- Principle:Huggingface Datatrove Text Extraction Framework
- Principle:TA Lib Ta lib python Technical Indicator Computation
- Principle:Microsoft Onnxruntime Input Data Preparation
- Principle:Heibaiying BigData Notes Spark Data Loading
Implementations
- Implementation:Eventual Inc Daft Read Csv
- Implementation:Volcengine Verl Initialize Tools From Config
- Implementation:Online ml River Forecaster Learn One
- Implementation:Neuml Txtai API Create
- Implementation:FlowiseAI Flowise AsyncDropdown
- Implementation:Ucbepic Docetl APIKeysDialog
- Implementation:SeleniumHQ Selenium QUnit
- Implementation:Intel Ipex llm GaLore Finetuning
- Implementation:Langchain ai Langchain BaseOpenAI LLM
- Implementation:Mlc ai Mlc llm Tokenizer
Heuristics
- Heuristic:Mlc ai Web llm Low Resource Model Selection
- Heuristic:Apache Druid Explore Compare Query Strategy
- Heuristic:Iamhankai Forest of Thought Input Length Overflow Recovery
- Heuristic:FMInference FlexLLMGen OOM Memory Management
- Heuristic:Nightwatchjs Nightwatch Safari Parallel Limitation
- Heuristic:Bitsandbytes foundation Bitsandbytes Outlier Threshold Detection
- Heuristic:Huggingface Transformers Gradient Checkpointing Memory Tradeoff
- Heuristic:Datahub project Datahub Emitter Selection Strategy
- Heuristic:DevExpress Testcafe Docker Chrome Tab Retry
- Heuristic:Apache Paimon Compression Tuning
Environments
- Environment:Haosulab ManiSkill Python SAPIEN Core
- Environment:Elevenlabs Elevenlabs python Python Websockets
- Environment:Lakeraai Pint benchmark Python 310 With Transformers
- Environment:FMInference FlexLLMGen NVMe Disk
- Environment:Huggingface Datatrove Slurm Cluster Environment
- Environment:Speechbrain Speechbrain Multi GPU DDP
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:Lm sys FastChat GPU CUDA Inference
- Environment:SeleniumHQ Selenium Selenium Manager Runtime
- Environment:Mbzuai oryx Awesome LLM Post training Python Pandas