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:Microsoft BIPIA White Box Defense Finetuning
- Workflow:Huggingface Open r1 Reasoning Data Generation
- Workflow:Rapidsai Cuml Time Series Forecasting
- Workflow:TA Lib Ta lib python Streaming Indicator Computation
- Workflow:Predibase Lorax Multi Adapter Merging
- Workflow:Alibaba MNN LLM Deployment Pipeline
- Workflow:NVIDIA NeMo Curator Semantic Deduplication
- Workflow:Facebookresearch Habitat lab Custom Task Extension
- Workflow:Lucidrains X transformers Autoregressive Language Modeling
- Workflow:FlagOpen FlagEmbedding Benchmark Evaluation
Principles
- Principle:Risingwavelabs Risingwave CDC PostgreSQL Schema Management
- Principle:Princeton nlp Tree of thought llm Usage Tracking
- Principle:Iamhankai Forest of Thought Majority Vote Consensus
- Principle:Neuml Txtai Content Indexing
- Principle:MaterializeInc Materialize Check Lifecycle
- Principle:Pyro ppl Pyro Time Series Forecasting
- Principle:CrewAIInc CrewAI Knowledge Attachment
- Principle:NVIDIA DALI Spatial Augmentation Detection
- Principle:Mistralai Client python File Upload
- Principle:Huggingface Datatrove HuggingFace Hub Writing
Implementations
- Implementation:Microsoft Semantic kernel FunctionChoiceBehavior Auto
- Implementation:Getgauge Taiko EmulateNetwork
- Implementation:Togethercomputer Together python Evaluation CLI
- Implementation:Recommenders team Recommenders ALSModel Transform
- Implementation:Truera Trulens UX Components
- Implementation:Hpcaitech ColossalAI Train ORPO Script
- Implementation:Mage ai Mage ai Chargebee Common Invoices Schema
- Implementation:Datajuicer Data juicer Job Monitor
- Implementation:Ray project Ray Ray Shutdown
- Implementation:OWASP Www project top 10 for large language model applications ASIFramework Map Architecture
Heuristics
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
- Heuristic:FMInference FlexLLMGen Weight Compression 4bit
- Heuristic:Langchain ai Langgraph Stream Mode Selection
- Heuristic:Open compass VLMEvalKit API Retry With Random Delay
- Heuristic:Apache Hudi Write Memory Tuning
- Heuristic:Apache Shardingsphere Shadow Routing Hint First Fallback
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Sgl project Sglang Schedule Conservativeness Tuning
- Heuristic:Marker Inc Korea AutoRAG Warning Deprecated Legacy QA Creation
- Heuristic:Lucidrains X transformers MaskGIT Generation Tuning
Environments
- Environment:Huggingface Open r1 Slurm Cluster
- Environment:OpenBMB UltraFeedback OpenAI API Environment
- Environment:Hiyouga LLaMA Factory Distributed Training Environment
- Environment:Volcengine Verl vLLM Rollout Environment
- Environment:FlagOpen FlagEmbedding Python PyTorch Environment
- Environment:Kornia Kornia ONNX Runtime Environment
- Environment:Puppeteer Puppeteer Node 18 Runtime
- Environment:NVIDIA NeMo Curator NVIDIA DALI
- Environment:Huggingface Datatrove Processing Dependencies
- Environment:Marker Inc Korea AutoRAG API Keys Configuration