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:Predibase Lorax Multi Adapter Merging
- Workflow:Google research Deduplicate text datasets Cross dataset deduplication
- Workflow:Lance format Lance Version Management
- Workflow:Evidentlyai Evidently Text Data Quality Evaluation
- Workflow:Trailofbits Fickling Pickle Decompilation and Tracing
- Workflow:Infiniflow Ragflow Document Processing Pipeline
- Workflow:ContextualAI HALOs Model Evaluation
- Workflow:InternLM Lmdeploy W4A16 AWQ Quantization
- Workflow:DataExpert io Data engineer handbook Dimensional Data Modeling Environment Setup
- Workflow:Volcengine Verl PPO Training With Reward Model
Principles
- Principle:Ggml org Llama cpp Memory Management
- Principle:Lucidrains X transformers Non Autoregressive Wrapper Setup
- Principle:Openai Openai node Audio Transcription
- Principle:Diagram of thought Diagram of thought Reasoning Path Analysis
- Principle:Explodinggradients Ragas Multi Turn Evaluation Schema
- Principle:Treeverse LakeFS GC Result Verification
- Principle:Ggml org Llama cpp Context Extension
- Principle:Guardrails ai Guardrails HubPackageManagement
- Principle:Axolotl ai cloud Axolotl LoRA Merging
- Principle:Astronomer Astronomer cosmos Airflow Plugin Documentation Hosting
Implementations
- Implementation:DistrictDataLabs Yellowbrick MissingValuesDispersion
- Implementation:Mlc ai Mlc llm Preshard
- Implementation:Treeverse LakeFS Java SDK Model CommPrefsInput
- Implementation:Lance format Lance Java OptimizeOptions
- Implementation:Trailofbits Fickling Activate Safe ML Environment
- Implementation:Liu00222 Open Prompt Injection binary search injection
- Implementation:Sgl project Sglang Fused MoE Marlin
- Implementation:Guardrails ai Guardrails Create Command Hub
- Implementation:Microsoft Playwright Client Input
- Implementation:Datajuicer Data juicer Check S3 Integration
Heuristics
- Heuristic:FlowiseAI Flowise Document Loader Bypass Optimization
- Heuristic:Snorkel team Snorkel NLP Preprocessor Memoization
- Heuristic:Apache Airflow Variable Access Pattern
- Heuristic:Huggingface Trl Distributed Device Map Override
- Heuristic:Webdriverio Webdriverio Click Interception Workaround
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:Kubeflow Kubeflow Issue Routing To Sub Repos
- Heuristic:FlagOpen FlagEmbedding Temperature Scaling Tip
- Heuristic:Roboflow Rf detr EMA Best Checkpoint Strategy
- Heuristic:Helicone Helicone Provider URL Regex Priority
Environments
- Environment:Diagram of thought Diagram of thought Python Graph Libraries
- Environment:Sgl project Sglang Distributed
- Environment:Iamhankai Forest of Thought Python CUDA Runtime
- Environment:Sgl project Sglang Performance Dashboard
- Environment:Apache Airflow Database Backend Environment
- Environment:OWASP Www project top 10 for large language model applications Pre Commit Hooks Environment
- Environment:Huggingface Alignment handbook DeepSpeed Multi Node
- Environment:Huggingface Transformers 3D Parallel Multi GPU
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Princeton nlp SimPO VLLM Inference