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:Confident ai Deepeval LLM Tracing and Observability
- Workflow:Groq Groq python Batch Processing
- Workflow:Roboflow Rf detr Custom Dataset Finetuning
- Workflow:NVIDIA NeMo Curator Video Curation Pipeline
- Workflow:Googleapis Python genai Context Caching
- Workflow:Ucbepic Docetl Long Document Chunking
- Workflow:Haifengl Smile Data Loading Pipeline
- Workflow:TA Lib Ta lib python Installation And Setup
- Workflow:Marker Inc Korea AutoRAG RAG Pipeline Optimization
- Workflow:Princeton nlp Tree of thought llm Adding new task
Principles
- Principle:FlagOpen FlagEmbedding Cross Encoder Reranking
- Principle:OpenRLHF OpenRLHF Iterative DPO
- Principle:Guardrails ai Guardrails Telemetry
- Principle:Hpcaitech ColossalAI Retrieval Augmented QA
- Principle:Haosulab ManiSkill Asset Download Loading
- Principle:Deepseek ai Janus Conversation Formatting
- Principle:InternLM Lmdeploy Chat Template Formatting
- Principle:Huggingface Datatrove Document Filtering Framework
- Principle:PrefectHQ Prefect Task Retry
- Principle:Langfuse Langfuse Export Completion Notification
Implementations
- Implementation:CrewAIInc CrewAI SerpApi Google Search Tool
- Implementation:Kornia Kornia Image Base
- Implementation:Marker Inc Korea AutoRAG Evaluator Init
- Implementation:OpenGVLab InternVL LLaVA Model Worker
- Implementation:Microsoft DeepSpeedExamples DeepSpeedRLHFEngine
- Implementation:Evidentlyai Evidently Legacy Base Suite
- Implementation:Truera Trulens Block Input Decorator
- Implementation:Onnx Onnx Helper Make Tensor Value Info
- Implementation:Axolotl ai cloud Axolotl Generate Examples Docs
- Implementation:Cypress io Cypress GetInstallMessage
Heuristics
- Heuristic:Marker Inc Korea AutoRAG Hybrid Retrieval Score Normalization
- Heuristic:FMInference FlexLLMGen Pin Memory Tradeoffs
- Heuristic:Google deepmind Dm control Warning Deprecated Legacy Base Walker
- Heuristic:Rapidsai Cuml CUDA Kernel Caching
- Heuristic:Mage ai Mage ai Record Deduplication Before Batch Export
- Heuristic:Obss Sahi Confidence Threshold Setting
- Heuristic:Intel Ipex llm Use Cache Training Vs Inference
- Heuristic:Apache Spark Serialization Optimization
- Heuristic:Cypress io Cypress Xvfb Display Gotcha
- Heuristic:Kserve Kserve NCCL RoCE Auto Detection
Environments
- Environment:Datajuicer Data juicer LLM API Credentials Environment
- Environment:VainF Torch Pruning YOLO Pruning Dependencies
- Environment:Tensorflow Tfjs Node Native Runtime
- Environment:BerriAI Litellm Python Runtime
- Environment:FlagOpen FlagEmbedding GPU Accelerator Environment
- Environment:Openai Whisper Numba
- Environment:Openclaw Openclaw Mintlify Documentation Platform
- Environment:Apache Airflow Database Backend Environment
- Environment:Bentoml BentoML NVIDIA GPU Resource
- Environment:LLMBook zh LLMBook zh github io Bitsandbytes Quantization Environment