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:Googleapis Python genai Multi Turn Chat
- Workflow:PeterL1n BackgroundMattingV2 Training pipeline
- Workflow:Triton inference server Server LLM Deployment With TRT LLM
- Workflow:Nightwatchjs Nightwatch Component Testing
- Workflow:CrewAIInc CrewAI Sequential Crew Execution
- Workflow:Elevenlabs Elevenlabs python Speech to Text Transcription
- Workflow:Langchain ai Langchain Release Process
- Workflow:Mlflow Mlflow Prompt Management
- Workflow:Vibrantlabsai Ragas Testset Generation
- Workflow:Huggingface Transformers Model Training With Trainer
Principles
- Principle:FMInference FlexLLMGen Runtime Configuration Constants
- Principle:Nautechsystems Nautilus trader Data Event Handling
- Principle:LLMBook zh LLMBook zh github io ALiBi Position Encoding
- Principle:Online ml River Online Feature Extraction
- Principle:Junyanz Pytorch CycleGAN and pix2pix Dataset Acquisition
- Principle:Eventual Inc Daft Arrow Export
- Principle:Heibaiying BigData Notes HBase Coprocessor Observer
- Principle:InternLM Lmdeploy AWQ Weight Quantization
- Principle:Romsto Speculative Decoding Ngram Storage
- Principle:Apache Dolphinscheduler Connection Lifecycle Management
Implementations
- Implementation:Zai org CogVideo DDIM CogVideoXPipeline From Pretrained
- Implementation:Elevenlabs Elevenlabs python Audio Output Utilities
- Implementation:Wandb Weave Publish PyPI Release
- Implementation:Risingwavelabs Risingwave ReplicationStream
- Implementation:Microsoft Onnxruntime PlotPipeline
- Implementation:Ggml org Llama cpp Adapter Header
- Implementation:Sgl project Sglang Multimodal Data Loading
- Implementation:Pyro ppl Pyro SVI Engine
- Implementation:Treeverse LakeFS Commit With Hooks
- Implementation:Marker Inc Korea AutoRAG Runner Run
Heuristics
- Heuristic:Alibaba MNN LLM Runtime Tuning
- Heuristic:Heibaiying BigData Notes Kafka Consumer Offset Strategy Tip
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Lm sys FastChat Conversation Splitting Token Buffer
- Heuristic:AnswerDotAI RAGatouille FAISS Vs PyTorch KMeans Indexing
- Heuristic:Openai Openai agents python Tool Choice Reset Prevents Loops
- Heuristic:Roboflow Rf detr Small Dataset Oversampling
- Heuristic:Langgenius Dify Warning Deprecated Default Datasource Auth
- Heuristic:Spotify Luigi Batch Parameter Aggregation
- Heuristic:Predibase Lorax LoRA Kernel Selection By Rank
Environments
- Environment:Neuml Txtai GPU Accelerator Environment
- Environment:LMCache LMCache Python Runtime
- Environment:Facebookresearch Habitat lab CUDA GPU Training Environment
- Environment:Online ml River Python Runtime Environment
- Environment:HKUDS AI Trader MCP Services
- Environment:Nightwatchjs Nightwatch Node 18 Runtime
- Environment:Haotian liu LLaVA OpenAI API Evaluation Environment
- Environment:Intel Ipex llm XPU Inference Environment
- Environment:Vibrantlabsai Ragas Google Drive Backend Environment
- Environment:Rapidsai Cuml Python RAPIDS Stack