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 Datatrove Summary Statistics
- Workflow:Microsoft Onnxruntime Python Inference Pipeline
- Workflow:Mbzuai oryx Awesome LLM Post training Awesome List Curation
- Workflow:Groq Groq python Chat Completion
- Workflow:Huggingface Trl GRPO Training
- Workflow:Open compass VLMEvalKit Image Benchmark Evaluation
- Workflow:Elevenlabs Elevenlabs python Realtime TTS Streaming
- Workflow:Lance format Lance Dataset Lifecycle
- Workflow:FlowiseAI Flowise Evaluation Pipeline
- Workflow:Danijar Dreamerv3 Distributed Parallel Training
Principles
- Principle:Langchain ai Langgraph Language Model Configuration
- Principle:Fastai Fastbook Collab Data Loading
- Principle:Lm sys FastChat Chat Data Cleaning
- Principle:Huggingface Diffusers ControlNet Output Refinement
- Principle:Googleapis Python genai Content Preparation
- Principle:Langgenius Dify Tool Integration
- Principle:Iterative Dvc Lockfile And Cache Update
- Principle:Apache Kafka JVM Classpath Assembly
- Principle:Ggml org Ggml Backend Initialization
- Principle:Online ml River Online Logistic Regression
Implementations
- Implementation:Bigscience workshop Petals ModuleContainer Create
- Implementation:Ggml org Ggml Sycl vecdotq
- Implementation:Huggingface Transformers Compute Basic Statistics
- Implementation:Anthropics Anthropic sdk python Stream Event Processing
- Implementation:Apache Spark Build Mvn
- Implementation:Open compass VLMEvalKit DoubaoVLWrapper
- Implementation:DistrictDataLabs Yellowbrick CVScores Visualizer
- Implementation:Fastai Fastbook Numericalize
- Implementation:Webdriverio Webdriverio XPath Converter
- Implementation:TobikoData Sqlmesh API Modules
Heuristics
- Heuristic:Openai Whisper SDPA Disabling For Attention Extraction
- Heuristic:Huggingface Datatrove Gopher Quality Thresholds
- Heuristic:MaterializeInc Materialize Dbt Transaction Disable
- Heuristic:Vibrantlabsai Ragas Temperature Sampling Strategy
- Heuristic:Huggingface Trl Gradient Checkpointing Use Reentrant
- Heuristic:BerriAI Litellm Retry Backoff Strategy
- Heuristic:Promptfoo Promptfoo Warning Deprecated Cache Migration
- Heuristic:Princeton nlp Tree of thought llm Global State Token Counting
- Heuristic:Vespa engine Vespa Document Batch Processing Strategy
- Heuristic:Sktime Pytorch forecasting Encoder Decoder Length Limits
Environments
- Environment:Danijar Dreamerv3 JAX CUDA
- Environment:Deepset ai Haystack Python Runtime Environment
- Environment:NVIDIA NeMo Aligner TensorRT LLM Acceleration Environment
- Environment:PacktPublishing LLM Engineers Handbook Docker MongoDB Qdrant Infrastructure
- Environment:Neuml Txtai Optional Extras Dependencies
- Environment:Facebookresearch Audiocraft XFormers Memory Efficient Attention
- Environment:Huggingface Datasets Lance Dependencies
- Environment:Alibaba ROLL ROCm GPU Environment
- Environment:Microsoft LoRA PyTorch CUDA Environment
- Environment:OpenBMB UltraFeedback HuggingFace Hub Environment