Main Page
27,667
Total Pages
1,118
Workflows
7,697
Principles
16,832
Implementations
1,245
Heuristics
909
Environments
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:Lm sys FastChat ShareGPT Data Pipeline
- Workflow:Predibase Lorax Single LoRA Inference
- Workflow:Wandb Weave Evaluation Pipeline
- Workflow:Huggingface Trl PPO RLHF Training
- Workflow:NVIDIA NeMo Aligner RLHF PPO Training
- Workflow:Lucidrains X transformers Autoregressive Language Modeling
- Workflow:Rapidsai Cuml GPU Clustering
- Workflow:ChenghaoMou Text dedup Benchmark Evaluation
- Workflow:Diagram of thought Diagram of thought DoT Trace Extraction
Principles
- Principle:ArroyoSystems Arroyo Graceful Shutdown
- Principle:DevExpress Testcafe Assertion Retry Logic
- Principle:Kserve Kserve Model Explainability
- Principle:Mlc ai Web llm Web Worker Engine Handler
- Principle:MarketSquare Robotframework browser Library Import and Configuration
- Principle:Eventual Inc Daft Iceberg Writing
- Principle:Google deepmind Mujoco Simulation Options Initialization
- Principle:Gretelai Gretel synthetics Timeseries Data Generation
- Principle:Eric mitchell Direct preference optimization Dataset Registration
- Principle:Deepset ai Haystack Documentation Navigation Structure
Implementations
- Implementation:Recommenders team Recommenders NCF NNI Utils
- Implementation:Openai Openai agents python Image Tool Output Pattern
- Implementation:Diagram of thought Diagram of thought Iterative Reasoner Prompt Loading
- Implementation:Onnx Onnx ArrayRef
- Implementation:Triton inference server Server L0 Model Queue Test
- Implementation:Openai Openai python Vector Store Update Params
- Implementation:Microsoft Playwright CssTokenizer
- Implementation:Teamcapybara Capybara XPathBuilder
- Implementation:DataTalksClub Data engineering zoomcamp Java JsonKStreamJoins
- Implementation:Getgauge Taiko ScrollTo
Heuristics
- Heuristic:Lucidrains X transformers MaskGIT Generation Tuning
- Heuristic:Danijar Dreamerv3 Replay Context Carry Init
- Heuristic:Microsoft Semantic kernel Function Choice Behavior Selection
- Heuristic:Openclaw Openclaw Cache TTL Asymmetric Strategy
- Heuristic:Wandb Weave Batch Processing Tuning
- Heuristic:Duckdb Duckdb Memory Management Rules
- Heuristic:Langchain ai Langgraph Deprecation Migration Guide
- Heuristic:Run llama Llama index Finetuning Warmup Steps
- Heuristic:Huggingface Open r1 Test Batch Early Termination
- Heuristic:ARISE Initiative Robomimic BatchNorm To GroupNorm For EMA
Environments
- Environment:Farama Foundation Gymnasium Box2D Physics Backend
- Environment:Kserve Kserve Cert Manager
- Environment:Eric mitchell Direct preference optimization Python Dependencies
- Environment:Mit han lab Llm awq CUDA Build Environment
- Environment:Langfuse Langfuse Redis 7 Queue Cache
- Environment:Neuml Txtai GPU Accelerator Detection
- Environment:Apache Spark Kubernetes Runtime
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:Lm sys FastChat SFT Training Environment
- Environment:Openai Openai agents python Python 3 9 Runtime