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:Puppeteer Puppeteer PDF Generation
- Workflow:Rapidsai Cuml GPU Clustering
- Workflow:Tencent Ncnn PyTorch Model Conversion and Inference
- Workflow:Mlc ai Web llm Basic Chat Completion
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:CrewAIInc CrewAI Knowledge RAG Pipeline
- Workflow:Explodinggradients Ragas Prompt Evaluation And Iteration
- Workflow:ARISE Initiative Robosuite Gymnasium RL Integration
- Workflow:Cohere ai Cohere python Text Embedding
- Workflow:Microsoft DeepSpeedExamples SuperOffload Finetuning
Principles
- Principle:Google deepmind Mujoco Sleep System
- Principle:Datahub project Datahub Protobuf Metadata Emission
- Principle:Mlflow Mlflow Code Quality Linting
- Principle:EvolvingLMMs Lab Lmms eval YAML Task Configuration
- Principle:FlowiseAI Flowise Credential Management
- Principle:Ggml org Llama cpp Ngram Speculative Drafting
- Principle:Togethercomputer Together python Audio Translation
- Principle:AUTOMATIC1111 Stable diffusion webui Internationalization
- Principle:Spotify Luigi Data Export
- Principle:Deepset ai Haystack Metadata Based Routing
Implementations
- Implementation:Haosulab ManiSkill URDFLoader
- Implementation:FMInference FlexLLMGen DeepSpeed Comm
- Implementation:Mlc ai Mlc llm MLC Chat Config
- Implementation:Pola rs Polars Polars Crate Cargo Config
- Implementation:BerriAI Litellm Service Types
- Implementation:Online ml River Rust Stats
- Implementation:Online ml River Utils Rolling
- Implementation:Mlc ai Mlc llm Qwen3 Model
- Implementation:Scikit learn Scikit learn StackingClassifier Init
- Implementation:Infiniflow Ragflow Vite Config
Heuristics
- Heuristic:AnswerDotAI RAGatouille Collection Size Index Tuning
- Heuristic:InternLM Lmdeploy OOM Troubleshooting
- Heuristic:Marker Inc Korea AutoRAG GPU Memory Cleanup Pattern
- Heuristic:Farama Foundation Gymnasium Render Mode Selection Guide
- Heuristic:Iterative Dvc YAML Dual Parser Strategy
- Heuristic:Mlfoundations Open flamingo RICES Feature Caching
- Heuristic:Openai Whisper Compression Ratio Threshold
- Heuristic:Facebookresearch Audiocraft Generation Parameter Defaults
- Heuristic:Unslothai Unsloth GGUF Quantization Selection
- Heuristic:Vespa engine Vespa RPM Zstd Compression Settings
Environments
- Environment:Norrrrrrr lyn WAInjectBench External Repos Dependencies
- Environment:Zai org CogVideo Video Captioning Environment
- Environment:Mlfoundations Open flamingo Evaluation Dependencies
- Environment:ContextualAI HALOs CUDA 12 1 Training Environment
- Environment:Interpretml Interpret Python Core Environment
- Environment:Mit han lab Llm awq Flash Attention Environment
- Environment:Pyro ppl Pyro Funsor Backend
- Environment:Run llama Llama index OpenAI API Configuration
- Environment:Huggingface Alignment handbook BitsAndBytes CUDA
- Environment:Sgl project Sglang CPU