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 Adding Partner Integration
- Workflow:Teamcapybara Capybara Custom Selector Definition
- Workflow:ArroyoSystems Arroyo Checkpoint Recovery
- Workflow:Explodinggradients Ragas Metric Prompt Optimization
- Workflow:TobikoData Sqlmesh Model development and testing
- Workflow:Sgl project Sglang Online Serving With OpenAI API
- Workflow:Gretelai Gretel synthetics DGAN Timeseries Generation
- Workflow:LaurentMazare Tch rs LLM Text Generation
- Workflow:Eventual Inc Daft Multimodal AI Batch Inference
- Workflow:Fastai Fastbook Collaborative Filtering
Principles
- Principle:Lucidrains X transformers Belief State Training
- Principle:Allenai Open instruct DPO Experiment Configuration
- Principle:Microsoft Onnxruntime Training Artifact Generation
- Principle:DevExpress Testcafe Tested Application Management
- Principle:Fede1024 Rust rdkafka Message Stream Processing
- Principle:Triton inference server Server Generate API
- Principle:Vllm project Vllm LoRA Request Creation
- Principle:Mlflow Mlflow Experiment Visualization
- Principle:Bitsandbytes foundation Bitsandbytes 8bit Optimizer State Quantization
- Principle:Langgenius Dify ModelManagement
Implementations
- Implementation:Risingwavelabs Risingwave Cargo Workspace Configuration
- Implementation:LMCache LMCache Config
- Implementation:Langchain ai Langgraph StateGraph Compile
- Implementation:Openai Openai python Upload Model
- Implementation:Ucbepic Docetl Directive ReduceGleaning
- Implementation:Turboderp org Exllamav2 Quant Layers
- Implementation:Mlc ai Mlc llm Ministral3 Loader
- Implementation:Microsoft Playwright Electron
- Implementation:Turboderp org Exllamav2 Ext QAttn
- Implementation:MaterializeInc Materialize Service Init
Heuristics
- Heuristic:Microsoft Onnxruntime Graph Optimization Level Selection
- Heuristic:Run llama Llama index Batch Eval Retry Strategy
- Heuristic:Langgenius Dify Celery Queue Separation
- Heuristic:Microsoft Playwright Browser Specific Workarounds
- Heuristic:Liu00222 Open Prompt Injection Attack Effectiveness Hierarchy
- Heuristic:Tensorflow Serving Warning Deprecated CreateTfrtSavedModel Raw
- Heuristic:ThreeSR Awesome Inference Time Scaling Date Parsing Fallback Tip
- Heuristic:ContextualAI HALOs TF32 Matmul Acceleration
- Heuristic:Mlc ai Mlc llm Optimization Level Selection
- Heuristic:Rapidsai Cuml CUDA Kernel Caching
Environments
- Environment:PacktPublishing LLM Engineers Handbook Unsloth Finetuning Environment
- Environment:OpenBMB UltraFeedback Python GPU Environment
- Environment:Mlc ai Mlc llm CUDA GPU Environment
- Environment:NVIDIA TransformerEngine GPU Compute Capability
- Environment:Facebookresearch Habitat lab HITL Runtime Environment
- Environment:OpenHands OpenHands Third Party Runtime Credentials
- Environment:Datahub project Datahub Frontend Build
- Environment:Risingwavelabs Risingwave Docker Deployment Environment
- Environment:FlowiseAI Flowise Queue Mode Environment
- Environment:Apache Hudi Flink Runtime Environment