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 RAG Pipeline Optimization
- Workflow:Interpretml Interpret Blackbox Model Explanation
- Workflow:Apache Druid SQL Query Execution
- Workflow:Datajuicer Data juicer Distributed Ray Processing
- Workflow:Langfuse Langfuse Otel ingestion pipeline
- Workflow:PacktPublishing LLM Engineers Handbook Feature Engineering
- Workflow:Truera Trulens RAG Evaluation With LangChain
- Workflow:Helicone Helicone LLM Response Normalization
- Workflow:Farama Foundation Gymnasium Policy Gradient Training
- Workflow:Huggingface Datatrove FineWeb Dataset Creation
Principles
- Principle:Webdriverio Webdriverio ESLint Plugin Architecture
- Principle:Langchain ai Langgraph Async Store Operations
- Principle:Kubeflow Pipelines Conditional Branching
- Principle:Getgauge Taiko Browser Closure
- Principle:MarketSquare Robotframework browser ES2015 Module Transpilation
- Principle:InternLM Lmdeploy Multimodal Inference
- Principle:Confident ai Deepeval Context Generation
- Principle:Huggingface Optimum Model Decomposition
- Principle:Deepseek ai Janus VQ VAE Decoding
- Principle:Ggml org Llama cpp Apple Platform Support
Implementations
- Implementation:Open compass VLMEvalKit PaliGemma
- Implementation:OWASP Www project top 10 for large language model applications GitHubActionChecker Check File
- Implementation:InternLM Lmdeploy Daily Ete Test
- Implementation:TobikoData Sqlmesh FileExplorer Context
- Implementation:Tensorflow Tfjs Models Test
- Implementation:Treeverse LakeFS Java SDK JSON
- Implementation:Neuml Txtai Embeddings Init
- Implementation:Haosulab ManiSkill Articulation
- Implementation:Run llama Llama index IngestionPipeline Run
- Implementation:Openai Openai node Beta RealtimeWS
Heuristics
- Heuristic:Apache Airflow Memory Management Tips
- Heuristic:Speechbrain Speechbrain Dynamic Mixing Parameters
- Heuristic:TA Lib Ta lib python STOCHRSI Vs STOCH RSI
- Heuristic:Allenai Open instruct Pre Init Torch Distributed
- Heuristic:CARLA simulator Carla Traffic Manager Sync Mode
- Heuristic:Sgl project Sglang Chunked Prefill OOM Prevention
- Heuristic:Elevenlabs Elevenlabs python VAD vs Manual Commit Strategy
- Heuristic:Apache Spark Build Fallback Strategies
- Heuristic:TobikoData Sqlmesh Model Change Categorization
- Heuristic:ContextualAI HALOs TF32 Matmul Acceleration
Environments
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Haosulab ManiSkill GPU CUDA Simulation
- Environment:Recommenders team Recommenders Python Core Dependencies
- Environment:Vllm project Vllm CUDA GPU Runtime
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Huggingface Peft Python Core Dependencies
- Environment:Intel Ipex llm Pipeline Parallel Environment
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime
- Environment:Deepspeedai DeepSpeed Multi Accelerator Environment
- Environment:Mit han lab Llm awq VILA Multimodal Environment