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:Ray project Ray Cross Language Invocation
- Workflow:AUTOMATIC1111 Stable diffusion webui Textual inversion training
- Workflow:Langgenius Dify RAG Pipeline Development
- Workflow:Arize ai Phoenix Prompt Management Pipeline
- Workflow:Langchain ai Langgraph Persistence and Memory Setup
- Workflow:Nautechsystems Nautilus trader Backtest with BacktestEngine
- Workflow:Diagram of thought Diagram of thought DoT Prompt Customization
- Workflow:Hpcaitech ColossalAI DPO Alignment
- Workflow:Confident ai Deepeval AI Agent Evaluation
- Workflow:Huggingface Open r1 Reasoning Data Generation
Principles
- Principle:Ggml org Llama cpp Fine Tuning
- Principle:Pytorch Serve IPEX Quantized Inference
- Principle:Marker Inc Korea AutoRAG Best Config Extraction
- Principle:Farama Foundation Gymnasium Atari Preprocessing
- Principle:Haifengl Smile Matrix Arithmetic
- Principle:Treeverse LakeFS Tag Creation
- Principle:FlowiseAI Flowise PWA Support
- Principle:Webdriverio Webdriverio Reporter Architecture
- Principle:Nautechsystems Nautilus trader Supply Chain Auditing
- Principle:Apache Kafka Release Notes Generation
Implementations
- Implementation:Huggingface Diffusers Custom Init Isort
- Implementation:Kubeflow Pipelines Taxi Utils
- Implementation:Lm sys FastChat Build Side By Side Arena Named UI
- Implementation:BerriAI Litellm Lowest TPM RPM Strategy
- Implementation:Webdriverio Webdriverio XPath Detection
- Implementation:Pyro ppl Pyro Util
- Implementation:Anthropics Anthropic sdk python Beta MessageCountTokensParams
- Implementation:Open compass VLMEvalKit CMMMU
- Implementation:Pola rs Polars Sink Operations
- Implementation:Facebookresearch Habitat lab RunningMeanAndVar
Heuristics
- Heuristic:Google research Deduplicate text datasets Variable Width Pointer Optimization
- Heuristic:Microsoft Playwright Test Stability Practices
- Heuristic:Mlc ai Mlc llm FlashInfer KV Cache Fallback
- Heuristic:LLMBook zh LLMBook zh github io BF16 Mixed Precision Default
- Heuristic:Anthropics Anthropic sdk python Model Deprecation Awareness
- Heuristic:Openai Openai node Stream Usage Interruption
- Heuristic:Infiniflow Ragflow Reranking Weight Tuning
- Heuristic:SeldonIO Seldon core Kafka Partition Throughput Tip
- Heuristic:ARISE Initiative Robomimic HDF5 Cache Mode Selection
- Heuristic:Webdriverio Webdriverio Default Timeout Configuration
Environments
- Environment:Vllm project Vllm AWS ECR
- Environment:Eric mitchell Direct preference optimization PyTorch CUDA
- Environment:NVIDIA DALI CUDA GPU Environment
- Environment:ARISE Initiative Robosuite GPU Rendering
- Environment:FlowiseAI Flowise Database Environment
- Environment:Huggingface Peft Optional Quantization Backends
- Environment:Google deepmind Mujoco MJX Warp CUDA Environment
- Environment:Bigscience workshop Petals Python Hivemind
- Environment:ARISE Initiative Robomimic HDF5 Data Dependencies
- Environment:NVIDIA DALI FFmpeg Environment