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:AnswerDotAI RAGatouille Document Indexing And Search
- Workflow:BerriAI Litellm Proxy Server Deployment
- Workflow:Microsoft Onnxruntime Nodejs Inference
- Workflow:Dotnet Machinelearning Time Series Forecasting
- Workflow:CarperAI Trlx RLHF Dialogue Alignment
- Workflow:Deepseek ai Janus Multimodal Understanding
- Workflow:Obss Sahi Sliced Inference Pipeline
- Workflow:NVIDIA DALI Image Preprocessing Pipeline
- Workflow:Elevenlabs Elevenlabs python Conversational AI Agent
- Workflow:InternLM Lmdeploy W8A8 SmoothQuant Quantization
Principles
- Principle:LaurentMazare Tch rs LLM Weight Conversion
- Principle:Lance format Lance Time Travel Queries
- Principle:CrewAIInc CrewAI Knowledge Ingestion
- Principle:Ollama Ollama GGUF Model Conversion Mistral
- Principle:Trailofbits Fickling Benchmark Payload Injection
- Principle:Speechbrain Speechbrain WER CER Evaluation For Whisper
- Principle:Langgenius Dify Document Processing Configuration
- Principle:Microsoft Onnxruntime Optimized Inference
- Principle:Sail sg LongSpec Draft Checkpoint Extraction
- Principle:LLMBook zh LLMBook zh github io LLaMA Decoder Layer
Implementations
- Implementation:Evidentlyai Evidently Legacy Engine
- Implementation:Kubeflow Kubeflow MLMD Pipelines Dashboard
- Implementation:Online ml River Neighbors KNNRegressor
- Implementation:Openai Evals Oaieval Run
- Implementation:Shiyu coder Kronos Train Model Predictor Qlib
- Implementation:Haosulab ManiSkill QuadrupedSpin
- Implementation:Lance format Lance MemWalIndex
- Implementation:Mage ai Mage ai Package Setup
- Implementation:Scikit learn Scikit learn PlottingBase
- Implementation:SeleniumHQ Selenium HasExtensions
Heuristics
- Heuristic:OpenBMB UltraFeedback GPU Memory Utilization
- Heuristic:Langgenius Dify Workflow Draft Hash Sync
- Heuristic:Mage ai Mage ai HTTP Error Classification
- Heuristic:CarperAI Trlx Batch Size Tuning
- Heuristic:Nautechsystems Nautilus trader Order Rate Limiting Configuration
- Heuristic:Langchain ai Langchain Warning Deprecated AnthropicLLM
- Heuristic:Trailofbits Fickling Race Condition Prevention
- Heuristic:ARISE Initiative Robosuite Hard Reset Vs Soft Reset
- Heuristic:Huggingface Datatrove MinHash Parameter Tuning
- Heuristic:ARISE Initiative Robosuite XML Reset Method Tradeoff
Environments
- Environment:Vllm project Vllm AArch64 CPU
- Environment:Pytorch Serve DeepSpeed Environment
- Environment:Openai Openai agents python Memory Extensions Dependencies
- Environment:Langchain ai Langgraph Docker Deployment Environment
- Environment:Onnx Onnx Python Runtime Environment
- Environment:Mlfoundations Open flamingo PyTorch CUDA Distributed
- Environment:OpenHands OpenHands SaaS Server Environment
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Openai Whisper Triton
- Environment:Microsoft BIPIA DeepSpeed Finetuning Environment