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:Duckdb Duckdb Code Generation Pipeline
- Workflow:InternLM Lmdeploy W8A8 SmoothQuant Quantization
- Workflow:ThreeSR Awesome Inference Time Scaling Manual Paper Contribution
- Workflow:Mlc ai Web llm Text Embeddings And RAG
- Workflow:Openclaw Openclaw Initial Setup And Onboarding
- Workflow:NVIDIA NeMo Aligner DPO Training
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:Mage ai Mage ai SQL Database Source Extraction
- Workflow:Facebookresearch Habitat lab Agent Benchmarking
- Workflow:Webdriverio Webdriverio Component Testing
Principles
- Principle:NVIDIA NeMo Aligner Reward Model Serving
- Principle:MarketSquare Robotframework browser Custom Keyword Invocation
- Principle:Datajuicer Data juicer Data Export
- Principle:Datahub project Datahub Quickstart Launch
- Principle:Mit han lab Llm awq Pseudo Quantization
- Principle:Spotify Luigi External Data Sources
- Principle:Duckdb Duckdb Random Number Generation
- Principle:CarperAI Trlx Reward Model Architecture
- Principle:Openai Openai agents python Streamed Run Invocation
- Principle:DataExpert io Data engineer handbook Windowed Aggregation
Implementations
- Implementation:Run llama Llama index MultiModalEmbedding
- Implementation:CarperAI Trlx GPTRewardModel
- Implementation:Mage ai Mage ai Twitter Ads Sync
- Implementation:Deepset ai Haystack Sidebars Navigation Config
- Implementation:Interpretml Interpret PseudoHuberRegressionObjective
- Implementation:Huggingface Datasets Dataset With Format For Tensors
- Implementation:Lance format Lance LegacyLogicalBinaryEncoding
- Implementation:NVIDIA TransformerEngine Ops L2Normalization
- Implementation:NVIDIA TransformerEngine Comm GEMM C API
- Implementation:Isaac sim IsaacGymEnvs Matplotlib3DPlotter
Heuristics
- Heuristic:Promptfoo Promptfoo Adaptive Concurrency Tuning
- Heuristic:Nautechsystems Nautilus trader Inflight Order Check Threshold
- Heuristic:Kubeflow Kubeflow Sequential Infrastructure Deployment
- Heuristic:CARLA simulator Carla Walker Spawn Vertical Offset
- Heuristic:Google research Deduplicate text datasets Parallel Job Scaling By Data Size
- Heuristic:Vespa engine Vespa Log Level Inheritance Polling
- Heuristic:Langgenius Dify Token Refresh Loop Prevention
- Heuristic:Turboderp org Exllamav2 Paged Cache Configuration
- Heuristic:Ggml org Llama cpp GPU Layer Offloading Verification
- Heuristic:Romsto Speculative Decoding Gamma Tuning
Environments
- Environment:TobikoData Sqlmesh BigQuery Connection
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Apache Shardingsphere Etcd Cluster Coordination
- Environment:Apache Spark Release Build Environment
- Environment:Bigscience workshop Petals Python Transformers
- Environment:Openclaw Openclaw State Directory And Credentials
- Environment:Mit han lab Llm awq VILA Multimodal Environment
- Environment:Heibaiying BigData Notes Flink 1 9 Environment
- Environment:Sgl project Sglang Triton
- Environment:HKUDS AI Trader Browser Runtime