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:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Teamcapybara Capybara Selenium Driver Configuration
- Workflow:Lm sys FastChat LoRA QLoRA Finetuning
- Workflow:Iterative Dvc Experiment Tracking
- Workflow:Langgenius Dify Workflow Builder and Execution
- Workflow:Unstructured IO Unstructured Document Partitioning
- Workflow:Sail sg LongSpec Speculative Decoding Inference
- Workflow:Getgauge Taiko Network Request Interception
- Workflow:Risingwavelabs Risingwave CDC Data Replication
- Workflow:OWASP Www project top 10 for large language model applications GenAI Red Team Testing
Principles
- Principle:Huggingface Trl Reward Sequence Classifier Loading
- Principle:PacktPublishing LLM Engineers Handbook LLM As Judge Evaluation
- Principle:FlagOpen FlagEmbedding Long Video Understanding Evaluation
- Principle:Apache Paimon Blob Descriptor Deserialization
- Principle:Ggml org Llama cpp HashingUtilities
- Principle:Infiniflow Ragflow Environment Configuration
- Principle:Treeverse LakeFS Documentation Site Configuration
- Principle:FlowiseAI Flowise Organization Management
- Principle:LLMBook zh LLMBook zh github io SFT Training Execution
- Principle:Ollama Ollama Model Manifest Creation
Implementations
- Implementation:Facebookresearch Audiocraft Checkpoint Manipulation
- Implementation:Online ml River Tree Nodes HTLeaf
- Implementation:Facebookresearch Habitat lab EQA Models
- Implementation:Vibrantlabsai Ragas Documentation Configuration
- Implementation:Online ml River Preprocessing TargetScalers
- Implementation:Langgenius Dify Plugin Auth Hooks
- Implementation:Interpretml Interpret RmseLogLinkRegressionObjective
- Implementation:Openai Openai python Batch List Params
- Implementation:Sdv dev SDV Run Diagnostic
- Implementation:Treeverse LakeFS ListRepositoryRuns
Heuristics
- Heuristic:Openclaw Openclaw Conservative Error Retry Classification
- Heuristic:Romsto Speculative Decoding Shared Tokenizer Requirement
- Heuristic:Iamhankai Forest of Thought UCB Exploration Constant
- Heuristic:Hpcaitech ColossalAI Gradient Checkpointing Memory Tip
- Heuristic:Allenai Open instruct NCCL CUMEM Disable
- Heuristic:Mlc ai Mlc llm Engine Mode Selection
- Heuristic:ARISE Initiative Robomimic BatchNorm To GroupNorm For EMA
- Heuristic:EvolvingLMMs Lab Lmms eval Request Caching Strategy
- Heuristic:Scikit learn Scikit learn Convergence Warning Handling
- Heuristic:Openclaw Openclaw Warning Suppression For Known Deprecations
Environments
- Environment:Vllm project Vllm Distributed
- Environment:Deepset ai Haystack GPU Device Environment
- Environment:Microsoft Playwright Platform Support Environment
- Environment:Speechbrain Speechbrain PyTorch CUDA Runtime
- Environment:Cleanlab Cleanlab Image Quality Dependencies
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Microsoft Semantic kernel DotNet SDK Environment
- Environment:Obss Sahi Python Image Processing
- Environment:Arize ai Phoenix OpenTelemetry SDK