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:HKUDS AI Trader Agent Decision Loop
- Workflow:Guardrails ai Guardrails Structured Data Generation
- Workflow:Langfuse Langfuse Batch export pipeline
- Workflow:Huggingface Datasets Dataset Loading and Exploration
- Workflow:Cohere ai Cohere python Model Finetuning
- Workflow:Lm sys FastChat MT Bench Evaluation
- Workflow:Openai Evals Running a single eval
- Workflow:Dagster io Dagster DSPy Optimization
- Workflow:Vespa engine Vespa Logging framework initialization
- Workflow:Google deepmind Mujoco Simulation benchmarking
Principles
- Principle:SeleniumHQ Selenium CDP Event Subscription
- Principle:DataExpert io Data engineer handbook SCD Type 2 Transformation
- Principle:Langgenius Dify Service Layer Architecture
- Principle:Neuml Txtai Training Data Preparation
- Principle:CrewAIInc CrewAI Semantic Retrieval
- Principle:Lucidrains X transformers Causal Decoder Configuration
- Principle:Unslothai Unsloth Ollama Deployment
- Principle:DataExpert io Data engineer handbook Test Data Construction
- Principle:Langgenius Dify Backend CLI
- Principle:Langgenius Dify Data Source Selection
Implementations
- Implementation:Hpcaitech ColossalAI PolicyLoss
- Implementation:Teamcapybara Capybara Queries BaseQuery
- Implementation:Sgl project Sglang Scalar Type
- Implementation:Sgl project Sglang Multimodal Data Loading
- Implementation:Mlfoundations Open flamingo Train one epoch
- Implementation:Huggingface Diffusers Quantization Config Classes
- Implementation:Mistralai Client python GCP ChatCompletionRequest
- Implementation:DevExpress Testcafe TestRunBookmark
- Implementation:CARLA simulator Carla ObjectLabel
- Implementation:Online ml River Bandit RandomPolicy
Heuristics
- Heuristic:Openai Openai agents python MCP Server Lifecycle Management
- Heuristic:Neuml Txtai Memory Streaming Optimization
- Heuristic:Apache Kafka JVM GC Tuning Defaults
- Heuristic:Alibaba ROLL Gradient Checkpointing Recomputation
- Heuristic:PeterL1n BackgroundMattingV2 ONNX Patch Method Compatibility
- Heuristic:Openai CLIP FP16 FP32 Dtype Handling
- Heuristic:Teamcapybara Capybara Negative Predicate Matching
- Heuristic:Lm sys FastChat Vicuna SFT Training Hyperparameters
- Heuristic:Protectai Modelscan Unknown Opcodes Assume Critical
- Heuristic:Mlc ai Web llm KV Cache Window Configuration
Environments
- Environment:Arize ai Phoenix Phoenix Server Runtime
- Environment:Marker Inc Korea AutoRAG Japanese NLP Dependencies
- Environment:Turboderp org Exllamav2 Flash Attention Backend
- Environment:NVIDIA NeMo Curator Video Codec Stack
- Environment:Tencent Ncnn Build Environment
- Environment:Bigscience workshop Petals CUDA Server
- Environment:Arize ai Phoenix Python Runtime
- Environment:Google deepmind Mujoco MJX JAX Environment
- Environment:Microsoft Autogen Studio Server Environment
- Environment:Intel Ipex llm NPU Cpp Environment