🤗 Transformers.js WebGPU Benchmark

This benchmark measures the execution time of BERT-based embedding models using the WASM and WebGPU execution providers across different batch sizes.

Options
WASM (int8)
WASM (fp16)
WASM (fp32)
WebGPU (fp16)
WebGPU (fp32)
Log scale (x)
Log scale (y)