Benchmark models using PyTorch and OpenVINO
Display leaderboard for earthquake intent classification models
Display leaderboard of language model evaluations
Merge machine learning models using a YAML configuration file
Display benchmark results
Calculate memory usage for LLM models
View and submit LLM benchmark evaluations
Track, rank and evaluate open LLMs and chatbots
Measure over-refusal in LLMs using OR-Bench
Benchmark LLMs in accuracy and translation across languages
Create and upload a Hugging Face model card
Submit models for evaluation and view leaderboard
Display and filter leaderboard models
OpenVINO Benchmark is a tool designed to benchmark models using PyTorch and OpenVINO. It allows users to compare the performance of models run through different frameworks, providing insights into speed, accuracy, and resource usage. This tool is particularly useful for optimizing model inference in production environments.
• Gapless PyTorch and OpenVINO Integration: Directly compare model performance between PyTorch and OpenVINO.
• Automated Model Conversion: Seamlessly convert PyTorch models to OpenVINO format for benchmarking.
• Comprehensive Performance Metrics: Measures inference speed, latency, throughput, and memory usage.
• Customizable Workloads: Allows users to define specific input shapes and batch sizes for accurate benchmarking.
• Cross-Architecture Support: Supports benchmarking on CPUs, GPUs, and other specialized hardware.
• Detailed Reporting: Generates clear and actionable reports for performance analysis.
What models are supported by OpenVINO Benchmark?
OpenVINO Benchmark supports models developed in PyTorch and compatible with OpenVINO. Models must be exported in a compatible format for benchmarking.
Can I use OpenVINO Benchmark on non-Intel hardware?
Yes, OpenVINO Benchmark supports benchmarking on various architectures, including non-Intel devices.
How do I interpret the benchmarking results?
Results are presented in a detailed report that compares metrics like inference speed, memory usage, and latency. This helps in identifying the most optimized framework for your use case.