⚡ WebGPU Benchmark Results – M1 Max xenova/gte-base --disable-dawn-robustness
#79
by
pcuenq
HF staff
- opened
| Batch Size | WebGPU (fp16) | WebGPU (fp32) |
| 1 | 38.70 | 60.40 |
| 2 | 72.70 | 117.00 |
| 4 | 129.30 | 219.80 |
| 8 | 251.00 | 436.00 |
| 16 | 484.10 | 855.60 |
| 32 | 954.40 | 1662.50 |
| 64 | 1911.60 | 3348.20 |
- Model: Xenova/gte-base
- Tests run: WebGPU (fp16), WebGPU (fp32)
- Sequence length: 512
- Browser: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36
- GPU: vendor=apple, architecture=common-3, device=, description=