tuannvhust/model_analyzer

Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

Triton Model Analyzer

LATEST RELEASE: You are currently on the main branch which tracks under-development progress towards the next release. The latest release of the Triton Model Analyzer is 1.25.0 and is available on branch r23.02.

Triton Model Analyzer is a CLI tool which can help you find a more optimal configuration, on a given piece of hardware, for single, multiple, or ensemble models running on a Triton Inference Server. Model Analyzer will also generate reports to help you better understand the trade-offs of the different configurations along with their compute and memory requirements.

Features

Search Modes

• Quick Search will sparsely search the Max Batch Size, Dynamic Batching, and Instance Group spaces by utilizing a heuristic hill-climbing algorithm to help you quickly find a more optimal configuration

• Automatic Brute Search will exhaustively search the Max Batch Size, Dynamic Batching, and Instance Group parameters of your model configuration

• Manual Brute Search allows you to create manual sweeps for every parameter that can be specified in the model configuration

Model Types

• Ensemble Model Search: Model Analyzer can help you find the optimal settings when profiling a non-BLS ensemble model, utilizing the Quick Search algorithm

• Multi-Model Search: EARLY ACCESS - Model Analyzer can help you find the optimal settings when profiling multiple concurrent models, utilizing the Quick Search algorithm

Other Features

• Detailed and summary reports: Model Analyzer is able to generate summarized and detailed reports that can help you better understand the trade-offs between different model configurations that can be used for your model.

• QoS Constraints: Constraints can help you filter out the Model Analyzer results based on your QoS requirements. For example, you can specify a latency budget to filter out model configurations that do not satisfy the specified latency threshold.
  
  

Examples and Tutorials

Single Model

See the Single Model Quick Start for a guide on how to use Model Analyzer to profile, analyze and report on a simple PyTorch model.

Multi Model

See the Multi-model Quick Start for a guide on how to use Model Analyzer to profile, analyze and report on two models running concurrently on the same GPU.

Documentation

• Installation
• Model Analyzer CLI
• Launch Modes
• Configuring Model Analyzer
• Model Analyzer Metrics
• Model Config Search
• Checkpointing
• Model Analyzer Reports
• Deployment with Kubernetes
  
  

Reporting problems, asking questions

We appreciate any feedback, questions or bug reporting regarding this project. When help with code is needed, follow the process outlined in the Stack Overflow (https://stackoverflow.com/help/mcve) document. Ensure posted examples are:

• minimal – use as little code as possible that still produces the same problem

• complete – provide all parts needed to reproduce the problem. Check if you can strip external dependency and still show the problem. The less time we spend on reproducing problems the more time we have to fix it

• verifiable – test the code you're about to provide to make sure it reproduces the problem. Remove all other problems that are not related to your request/question.