Measure execution times of BERT models using WebGPU and WASM
View and submit LLM benchmark evaluations
Explore and visualize diverse models
View LLM Performance Leaderboard
Evaluate reward models for math reasoning
Determine GPU requirements for large language models
Evaluate open LLMs in the languages of LATAM and Spain.
Upload a machine learning model to Hugging Face Hub
View and submit language model evaluations
Compare LLM performance across benchmarks
Display LLM benchmark leaderboard and info
Evaluate LLM over-refusal rates with OR-Bench
Display leaderboard for earthquake intent classification models
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.