Measure execution times of BERT models using WebGPU and WASM
Request model evaluation on COCO val 2017 dataset
View LLM Performance Leaderboard
Explore and submit models using the LLM Leaderboard
Evaluate code generation with diverse feedback types
Upload a machine learning model to Hugging Face Hub
Run benchmarks on prediction models
Benchmark AI models by comparison
Evaluate AI-generated results for accuracy
Calculate memory needed to train AI models
Predict customer churn based on input details
Find and download models from Hugging Face
Browse and submit evaluations for CaselawQA benchmarks
WebGPU Embedding Benchmark is a tool designed to measure the execution times of BERT models using WebGPU and WebAssembly (WASM). It helps developers and researchers evaluate the performance of embedding models in web-based environments, leveraging modern graphics technologies for accelerated computations.
• WebGPU Acceleration: Leverages WebGPU for hardware-accelerated computations. • WASM Execution: Utilizes WebAssembly for efficient model inference. • Detailed Timing Measurements: Provides precise execution time metrics for model inference. • Cross-Platform Compatibility: Runs on modern web browsers supporting WebGPU. • Model Optimization Insights: Offers benchmarks to guide model optimization strategies. • Performance Comparison: Enables comparison of performance across different hardware setups.
What does WebGPU Embedding Benchmark measure?
It measures the execution time of BERT models using WebGPU and WASM, providing insights into performance bottlenecks.
Which browsers support WebGPU?
As of now, browsers like Chrome, Firefox, and Edge provide experimental or full support for WebGPU.
Why is WebGPU combined with WASM for this benchmark?
WebGPU offers hardware acceleration, while WASM provides efficient computation, making them a powerful combination for high-performance web-based model inference.