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:Datahub project Datahub Docker Quickstart Deployment
- Workflow:Microsoft Playwright Trace recording and debugging
- Workflow:Zai org CogVideo Diffusers Text to Video Inference
- Workflow:Rapidsai Cuml Time Series Forecasting
- Workflow:EvolvingLMMs Lab Lmms eval End to End Evaluation
- Workflow:Interpretml Interpret EBM Model Merging
- Workflow:Neuml Txtai RAG Pipeline
- Workflow:Apache Dolphinscheduler Workflow Failover Recovery
- Workflow:Openai Openai python Embeddings Generation
- Workflow:Pytorch Serve Model Deployment
Principles
- Principle:Mlflow Mlflow Training Execution
- Principle:Spcl Graph of thoughts Keyword Counting Prompt Design
- Principle:Ggml org Llama cpp Unicode Text Processing
- Principle:Microsoft LoRA LoRA Training Loop
- Principle:EvolvingLMMs Lab Lmms eval PassAtK Evaluation
- Principle:Apache Beam Element Bundling
- Principle:Langgenius Dify Documentation
- Principle:Lance format Lance Tag Management
- Principle:TobikoData Sqlmesh Forward Only Change Handling
- Principle:FMInference FlexLLMGen AIO Performance Benchmarking
Implementations
- Implementation:Roboflow Rf detr Supervision Annotators
- Implementation:Online ml River Anomaly PAD
- Implementation:Microsoft Agent framework AzureOpenAIResponsesClient Init
- Implementation:Interpretml Interpret PartitionMultiDimensionalTree
- Implementation:Microsoft Autogen Studio Agent Fields
- Implementation:Interpretml Interpret Gradient Histogram Bin
- Implementation:LaurentMazare Tch rs Tensor Iter
- Implementation:Online ml River Utils Norm
- Implementation:Teamcapybara Capybara Session Visit
- Implementation:Mage ai Mage ai Chargebee Common Invoices Schema
Heuristics
- Heuristic:Langfuse Langfuse LLM Rate Limit 24h Abandon
- Heuristic:TobikoData Sqlmesh Execution Time Caching
- Heuristic:Apache Airflow Scheduler Performance Tuning
- Heuristic:Langfuse Langfuse Eval Loop Prevention
- Heuristic:Helicone Helicone Provider URL Regex Priority
- Heuristic:Unslothai Unsloth VLLM Memory Utilization
- Heuristic:MarketSquare Robotframework browser MacOS Sonoma Startup Delay
- Heuristic:Fastai Fastbook Mixup Data Augmentation
- Heuristic:InternLM Lmdeploy KV Quantization Tradeoffs
- Heuristic:Sgl project Sglang Memory Fraction Tuning
Environments
- Environment:CARLA simulator Carla Python API Runtime
- Environment:NVIDIA NeMo Curator Video Codec Stack
- Environment:NVIDIA NeMo Curator RAPIDS GPU Stack
- Environment:Vibrantlabsai Ragas Python 3 9 Core Environment
- Environment:Marker Inc Korea AutoRAG GPU PyTorch Environment
- Environment:InternLM Lmdeploy CUDA GPU Runtime
- Environment:VainF Torch Pruning CUDA GPU Benchmarking
- Environment:Fede1024 Rust rdkafka Kafka Broker Runtime
- Environment:Run llama Llama index Python LlamaIndex Core
- Environment:Farama Foundation Gymnasium Python 3 10 Runtime