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:Farama Foundation Gymnasium Policy Gradient Training
- Workflow:Gretelai Gretel synthetics LSTM Text Generation
- Workflow:Openai CLIP Prompt engineered classification
- Workflow:PrefectHQ Prefect Web Scraping Pipeline
- Workflow:OpenHands OpenHands Third Party Runtime Integration
- Workflow:Haifengl Smile SQL Analytics Pipeline
- Workflow:Apache Paimon Vector Similarity Search
- Workflow:Sktime Pytorch forecasting NBeats Univariate Forecasting
- Workflow:Princeton nlp Tree of thought llm Baseline comparison
- Workflow:Google deepmind Dm control MJCF Model Composition
Principles
- Principle:Spotify Luigi Worker Scheduler Communication
- Principle:Bitsandbytes foundation Bitsandbytes FSDP Quant State Recovery
- Principle:Rapidsai Cuml Synthetic Dataset Generation
- Principle:ArroyoSystems Arroyo Connection Table Configuration
- Principle:BerriAI Litellm Database Setup
- Principle:Openclaw Openclaw Context Assembly
- Principle:Haosulab ManiSkill Environment Configuration
- Principle:Interpretml Interpret Synthetic Data
- Principle:Openai Openai python Realtime Session Configuration
- Principle:Langchain ai Langgraph Runtime Context
Implementations
- Implementation:Teamcapybara Capybara Session Matchers Assert Current Path
- Implementation:Farama Foundation Gymnasium Space Base
- Implementation:Pola rs Polars Filter by Time Range
- Implementation:Mit han lab Llm awq LMEvalAdaptor
- Implementation:Apache Hudi ClusteringUtil ValidateClusteringScheduling
- Implementation:AUTOMATIC1111 Stable diffusion webui Config States
- Implementation:Facebookresearch Habitat lab VER ReportWorker
- Implementation:Datajuicer Data juicer PythonLambdaMapper
- Implementation:ClickHouse ClickHouse Poco IPAddress Impl
- Implementation:Triton inference server Server L0 Long Running Stress Scenarios
Heuristics
- Heuristic:DevExpress Testcafe Docker Chrome Tab Retry
- Heuristic:Openai Evals Chat Format Recommendation
- Heuristic:Mlflow Mlflow Nested Run Organization
- Heuristic:ClickHouse ClickHouse Test Writing Conventions
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Intel Ipex llm Use Cache Training Vs Inference
- Heuristic:Tencent Ncnn Lightmode Memory Optimization
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Tencent Ncnn Thread Count Tuning
- Heuristic:Anthropics Anthropic sdk python Adaptive Thinking Over Enabled
Environments
- Environment:Huggingface Datasets Audio Video Dependencies
- Environment:Huggingface Transformers PEFT Adapter Env
- Environment:Lm sys FastChat Python Core Dependencies
- Environment:Wandb Weave Trace Server Infrastructure
- Environment:Microsoft Onnxruntime Nodejs Runtime Environment
- Environment:Vibrantlabsai Ragas Optional NLP Metrics Environment
- Environment:Apache Hudi Flink Runtime Environment
- Environment:Heibaiying BigData Notes Storm 1 2 Environment
- Environment:LMCache LMCache VLLM Serving Engine
- Environment:FMInference FlexLLMGen NVMe Disk