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:VainF Torch Pruning CNN Pruning
- Workflow:Microsoft BIPIA Attack Success Rate Evaluation
- Workflow:Nautechsystems Nautilus trader Data loading and cataloging
- Workflow:CrewAIInc CrewAI Custom Tool Integration
- Workflow:Openai Openai python Realtime Conversation
- Workflow:Huggingface Datatrove Common Crawl Processing
- Workflow:Mlc ai Web llm Web Worker Deployment
- Workflow:DataExpert io Data engineer handbook PySpark Iceberg Job Execution
- Workflow:Fede1024 Rust rdkafka At Least Once Processing
- Workflow:Huggingface Peft LoRA Causal LM Finetuning
Principles
- Principle:Openai Whisper Dynamic Time Warping
- Principle:Scikit learn Scikit learn Online Learning
- Principle:Teamcapybara Capybara Server And Options Configuration
- Principle:ClickHouse ClickHouse Binary Linking
- Principle:Togethercomputer Together python Client Initialization
- Principle:CARLA simulator Carla Waypoint Queue Completion
- Principle:Heibaiying BigData Notes Hive Partitioning and Bucketing
- Principle:Microsoft Onnxruntime Session Options Configuration
- Principle:Openai Openai python Fine Tuning Job Monitoring
- Principle:DataExpert io Data engineer handbook SparkSession Test Fixture
Implementations
- Implementation:Langchain ai Langchain Chroma Constructor
- Implementation:Hpcaitech ColossalAI Reward Utils
- Implementation:Astronomer Astronomer cosmos Cluster Policy
- Implementation:Huggingface Optimum MetaAwareMethodsPatcher
- Implementation:Protectai Llm guard Output Toxicity
- Implementation:FMInference FlexLLMGen Data Wrangling Install
- Implementation:BerriAI Litellm Passthrough Utils
- Implementation:Datahub project Datahub Pre Commit Config
- Implementation:Microsoft Semantic kernel InMemoryVectorStore
- Implementation:Onnx Onnx IR Protobuf Converter
Heuristics
- Heuristic:DevExpress Testcafe Window Resize Correction
- Heuristic:Bigscience workshop Petals NF4 Quantization Default On CUDA
- Heuristic:Eventual Inc Daft Delta Lake S3 Locking
- Heuristic:Obss Sahi Class Agnostic vs Per Class NMS
- Heuristic:Huggingface Datatrove Gopher Quality Thresholds
- Heuristic:Tensorflow Serving GPU Memory And CPU Optimization
- Heuristic:Vespa engine Vespa Maven Parallel Build Optimization
- Heuristic:DataExpert io Data engineer handbook Docker Volume Persistence Management
- Heuristic:LLMBook zh LLMBook zh github io Deduplication Ngram Threshold
- Heuristic:DistrictDataLabs Yellowbrick Scikit Learn API Compatibility
Environments
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Datahub project Datahub Java 17 Backend Environment
- Environment:Online ml River Python Runtime Environment
- Environment:Vllm project Vllm CUDA Runtime
- Environment:OpenHands OpenHands Integration Credentials
- Environment:Vllm project Vllm ROCm
- Environment:OpenRLHF OpenRLHF vLLM Environment
- Environment:Dagster io Dagster Container Resource Monitoring
- Environment:Openai Openai agents python LiteLLM Dependencies
- Environment:Speechbrain Speechbrain HuggingFace Transformers