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:Huggingface Optimum FX Graph Optimization
- Workflow:Microsoft Playwright Browser automation CLI
- Workflow:Huggingface Trl Direct Preference Optimization
- Workflow:LMCache LMCache P2P KV Cache Sharing
- Workflow:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Lucidrains X transformers Non Autoregressive Masked Generation
- Workflow:Deepspeedai DeepSpeed ZeRO Distributed Training
- Workflow:Interpretml Interpret Model Explanation And Visualization
- Workflow:Huggingface Diffusers ControlNet Guided Generation
- Workflow:Mlfoundations Open flamingo Distributed Training
Principles
- Principle:Huggingface Datatrove Random Sampling
- Principle:Langgenius Dify Single Node Testing
- Principle:Langchain ai Langchain Retriever Integration
- Principle:Ollama Ollama Compute Graph System
- Principle:Pytorch Serve Model Explainability
- Principle:SeldonIO Seldon core HuggingFace Text Inference
- Principle:Helicone Helicone App Provider Composition
- Principle:Anthropics Anthropic sdk python Client Initialization
- Principle:Lm sys FastChat Model Weight Delta Distribution
- Principle:Deepset ai Haystack Extractive Question Answering
Implementations
- Implementation:CrewAIInc CrewAI RAG CSV Loader
- Implementation:Infiniflow Ragflow DataflowResult Page
- Implementation:Microsoft DeepSpeedExamples Load Model SuperOffload
- Implementation:Ollama Ollama Convert NomicBert
- Implementation:Roboflow Rf detr RFDETR Train Config
- Implementation:DevExpress Testcafe TestController Actions
- Implementation:CrewAIInc CrewAI Docs Navigation Config
- Implementation:Huggingface Datatrove Document
- Implementation:Facebookresearch Habitat lab Benchmark evaluate
- Implementation:Ggml org Llama cpp Convert LoRA To GGUF
Heuristics
- Heuristic:Cleanlab Cleanlab KNN Distance Metric Selection
- Heuristic:Huggingface Optimum GPTQ Quantization Defaults
- Heuristic:Cohere ai Cohere python HTTP Retry Backoff Strategy
- Heuristic:Mlc ai Web llm Tokenizer JSON Preference
- Heuristic:Duckdb Duckdb Sanitizer Configuration
- Heuristic:Fede1024 Rust rdkafka Queue Buffering Priority
- Heuristic:Obss Sahi Auto Slice Resolution
- Heuristic:Apache Druid Cluster Health Diagnostic Thresholds
- Heuristic:Huggingface Peft Warning Deprecated Bone
- Heuristic:Tencent Ncnn Thread Count Tuning
Environments
- Environment:Marker Inc Korea AutoRAG Korean NLP Dependencies
- Environment:Unstructured IO Unstructured GitHub Actions
- Environment:TobikoData Sqlmesh Python Runtime
- Environment:Anthropics Anthropic sdk python Python SDK Core Environment
- Environment:Duckdb Duckdb Code Generation Tools
- Environment:SeldonIO Seldon core Kubernetes Cluster Environment
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:Ggml org Ggml Metal GPU Environment
- Environment:NVIDIA NeMo Curator NVIDIA DALI
- Environment:Open compass VLMEvalKit GPU CUDA Environment