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:Zai org CogVideo SAT Video Generation
- Workflow:Confident ai Deepeval LLM Tracing and Observability
- Workflow:DistrictDataLabs Yellowbrick Regression Model Evaluation
- Workflow:Ggml org Llama cpp Speculative Decoding
- Workflow:Apache Druid Batch Data Ingestion
- Workflow:Facebookresearch Audiocraft EnCodec Compression Training
- Workflow:Deepspeedai DeepSpeed Sequence Parallel Long Context Training
- Workflow:Facebookresearch Audiocraft MusicGen Training Pipeline
- Workflow:Vibrantlabsai Ragas Prompt Optimization
- Workflow:Evidentlyai Evidently ML Model Quality Report
Principles
- Principle:TA Lib Ta lib python Installation Verification
- Principle:OpenGVLab InternVL Segmentation Dataset Configuration
- Principle:Eventual Inc Daft Column Input Normalization
- Principle:Apache Beam Heartbeat and Refresh
- Principle:Google research Deduplicate text datasets TFDS Deduplication Application
- Principle:Protectai Llm guard Regex Pattern Matching
- Principle:Datahub project Datahub Action Pipeline Configuration
- Principle:OpenGVLab InternVL Flash Attention Patching
- Principle:Microsoft LoRA GLUE Data Download
- Principle:Huggingface Alignment handbook Model Saving and Publishing
Implementations
- Implementation:CrewAIInc CrewAI RAG Base Chunker
- Implementation:Scikit learn Scikit learn Permutation Importance
- Implementation:Hiyouga LLaMA Factory Data Formatter
- Implementation:Infiniflow Ragflow MetadataManageValuesModal Component
- Implementation:PacktPublishing LLM Engineers Handbook HfApi Model Info
- Implementation:Ggml org Llama cpp RPC Server
- Implementation:Mit han lab Llm awq InternVL Benchmark
- Implementation:Predibase Lorax Flash Gemma2 Modeling
- Implementation:Lance format Lance JNI Transaction
- Implementation:Tensorflow Serving Resnet K8s Manifest
Heuristics
- Heuristic:Promptfoo Promptfoo WAL Mode Network Filesystem
- Heuristic:Bentoml BentoML Warning Deprecated Runner Class
- Heuristic:Zai org CogVideo Frame Count and Resolution Constraints
- Heuristic:Alibaba MNN Warning Deprecated Winograd Codegen
- Heuristic:Cohere ai Cohere python Warning Deprecated Legacy Generate API
- Heuristic:SqueezeAILab ETS Max Depth And Token Guards
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Dotnet Machinelearning Text File Sampling Strategy
- Heuristic:OpenGVLab InternVL Packed Training Buffer Management
- Heuristic:Apache Beam Lock Contention Batching
Environments
- Environment:Langgenius Dify Docker Deployment Environment
- Environment:OpenBMB UltraFeedback vLLM Multi GPU Environment
- Environment:Predibase Lorax CUDA GPU Runtime
- Environment:Apache Dolphinscheduler Netty Runtime
- Environment:Ggml org Ggml C Cpp Build Environment
- Environment:Marker Inc Korea AutoRAG API Keys And Credentials
- Environment:Deepspeedai DeepSpeed XPU Environment
- Environment:Teamcapybara Capybara Selenium WebDriver Environment
- Environment:Iterative Dvc DVC Environment Variables
- Environment:Guardrails ai Guardrails Docker Server Runtime