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:Langchain ai Langchain Chat Model Invocation
- Workflow:Rapidsai Cuml Sklearn Zero Code Acceleration
- Workflow:Cohere ai Cohere python Tool Use Agentic Chat
- Workflow:Triton inference server Server Ensemble Model Pipeline
- Workflow:Vllm project Vllm Structured Output Generation
- Workflow:Princeton nlp SimPO Model Inference
- Workflow:DevExpress Testcafe CLI Test Execution
- Workflow:Helicone Helicone LLM Request Proxy Logging
- Workflow:Google research Deduplicate text datasets Cross dataset deduplication
- Workflow:Ollama Ollama Custom Model Creation
Principles
- Principle:LaurentMazare Tch rs Tensor Format Conversion
- Principle:Microsoft Semantic kernel Orchestration Result Collection
- Principle:Ucbepic Docetl Blocking Threshold Optimization
- Principle:Huggingface Datatrove Local Pipeline Execution
- Principle:Ggml org Llama cpp GPU Inference
- Principle:Microsoft Agent framework Human in the Loop Response
- Principle:Groq Groq python Batch Input Preparation
- Principle:Google deepmind Mujoco GLFW Window Management
- Principle:TobikoData Sqlmesh Dev Environment Testing For Incremental
- Principle:Googleapis Python genai Training Dataset Preparation
Implementations
- Implementation:Googleapis Python genai Sphinx SearchTools
- Implementation:NVIDIA TransformerEngine JAX Attention
- Implementation:Openai Openai node Beta Realtime Resource
- Implementation:Ggml org Ggml Sycl element wise
- Implementation:Open compass VLMEvalKit Check Command
- Implementation:Openai Openai agents python ShellTool Pattern
- Implementation:Lance format Lance Java CompactionTask
- Implementation:ArroyoSystems Arroyo Datastream Optimizers
- Implementation:Langgenius Dify UpdateFromMarketPlace
- Implementation:ARISE Initiative Robomimic TensorUtils list of flat dict to dict of list
Heuristics
- Heuristic:Alibaba MNN Backend Selection Guide
- Heuristic:Protectai Modelscan Stricter Zip Detection
- Heuristic:Mlc ai Web llm Penalty Parameter Defaults
- Heuristic:ThreeSR Awesome Inference Time Scaling API Rate Limiting Tip
- Heuristic:Roboflow Rf detr Resolution Divisibility Rule
- Heuristic:Langchain ai Langchain Deprecation Version Tracking
- Heuristic:Arize ai Phoenix Environment Variable Precedence
- Heuristic:Junyanz Pytorch CycleGAN and pix2pix Batch Size One Default
- Heuristic:Huggingface Open r1 Code Execution Timeout Strategy
- Heuristic:Roboflow Rf detr Layer Wise LR Decay
Environments
- Environment:Romsto Speculative Decoding CUDA PyTorch
- Environment:Hpcaitech ColossalAI ColossalQA RAG Environment
- Environment:Intel Ipex llm RAG LangChain Environment
- Environment:Intel Ipex llm Build Environment
- Environment:Microsoft Agent framework API Credentials
- Environment:Huggingface Open r1 CUDA Environment
- Environment:Obss Sahi Python Pycocotools
- Environment:Langfuse Langfuse ClickHouse Analytics
- Environment:Mlflow Mlflow OpenAI LLM Integration Environment
- Environment:Huggingface Datatrove IO Dependencies