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:Marker Inc Korea AutoRAG Pipeline Deployment
- Workflow:Langchain ai Langchain Streaming Responses
- Workflow:Hpcaitech ColossalAI Model Evaluation
- Workflow:Gretelai Gretel synthetics DGAN Timeseries Generation
- Workflow:ChenghaoMou Text dedup MinHash LSH Deduplication
- Workflow:Sdv dev SDV Sequential data synthesis
- Workflow:HKUDS AI Trader Agent Decision Loop
- Workflow:Allenai Open instruct DPO Preference Tuning
- Workflow:Datahub project Datahub Spark Lineage Capture
- Workflow:Vespa engine Vespa Linguistics text processing pipeline
Principles
- Principle:Webdriverio Webdriverio Reporter Architecture
- Principle:Alibaba ROLL LLM Response Generation
- Principle:Eventual Inc Daft API Boundary Protection
- Principle:Norrrrrrr lyn WAInjectBench Ensemble Aggregation Image
- Principle:CARLA simulator Carla Traffic Behavior Configuration
- Principle:Run llama Llama index Finetuned Model Retrieval
- Principle:CrewAIInc CrewAI Task Definition
- Principle:Confident ai Deepeval Evaluation Dataset Preparation
- Principle:Mage ai Mage ai Catalog Selection
- Principle:Confident ai Deepeval LLM Evaluation Metrics
Implementations
- Implementation:Pyro ppl Pyro ProvenanceTensor
- Implementation:Mlc ai Web llm Prebuilt App Config
- Implementation:Microsoft Playwright SocksClientCertificatesInterceptor
- Implementation:Apache Druid CompactionConfigDialog
- Implementation:Open compass VLMEvalKit ImageShortQADataset
- Implementation:Googleapis Python genai LocalTokenizer
- Implementation:Openai Openai agents python ItemHelpers
- Implementation:CrewAIInc CrewAI Enterprise API Spec Base
- Implementation:Huggingface Transformers Check Copies
- Implementation:ClickHouse ClickHouse TCPServer Start
Heuristics
- Heuristic:Turboderp org Exllamav2 Attention Backend Selection
- Heuristic:EvolvingLMMs Lab Lmms eval Memory Cleanup After Inference
- Heuristic:Romsto Speculative Decoding Gamma Tuning
- Heuristic:Datahub project Datahub Git Worktree Gradle Fix
- Heuristic:Lm sys FastChat Flash Attention GPU Requirements
- Heuristic:Datahub project Datahub Secret Handling And Deprecation Patterns
- Heuristic:Bigscience workshop Petals Randomized Rebalancing Intervals
- Heuristic:Spcl Graph of thoughts Four Bit Quantization For Local LLMs
- Heuristic:Neuml Txtai Thread Safety Constraints
- Heuristic:Pola rs Polars Streaming For Large Datasets
Environments
- Environment:Alibaba MNN GPU CUDA Environment
- Environment:Google deepmind Mujoco C Build Environment
- Environment:Testtimescaling Testtimescaling github io GitHub Actions Runner
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Evidentlyai Evidently Grafana Monitoring Environment
- Environment:Mlc ai Web llm Chrome Extension Manifest V3
- Environment:AUTOMATIC1111 Stable diffusion webui Xformers Attention
- Environment:Alibaba MNN GPU OpenCL Environment
- Environment:Vllm project Vllm CUDA
- Environment:MaterializeInc Materialize Python CI Builder Runtime