⚡ WebGPU Benchmark Results (96.86x speedup) – M1 Max gte-base
#61
by
pcuenq
HF staff
- opened
Batch Size | WASM (fp16) | WASM (fp32) | WebGPU (fp16) | WebGPU (fp32) |
1 | 2659.10 | 2563.40 | 58.30 | 63.00 |
2 | 5303.50 | 5117.80 | 92.80 | 121.20 |
4 | 10818.80 | 10355.70 | 153.50 | 217.30 |
8 | 21918.50 | 20919.00 | 272.90 | 422.60 |
16 | 45144.90 | 42750.00 | 499.10 | 818.10 |
32 | 93328.40 | 87487.90 | 963.50 | 1641.50 |
- Model: Xenova/gte-base
- Tests run: WASM (fp16), WASM (fp32), 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/122.0.0.0 Safari/537.36
- GPU: vendor=apple, architecture=common-3, device=, description=