⚡ WebGPU Benchmark Results (4.79x speedup) - Ubuntu 3090 Ti
#52
by
pcuenq
HF staff
- opened
Batch Size | WebGPU (fp16) | WebGPU (fp32) |
1 | 46.80 | 28.60 |
2 | 56.70 | 50.60 |
4 | 67.90 | 96.80 |
8 | 52.00 | 285.30 |
16 | 58.20 | 47.00 |
32 | 80.80 | 89.80 |
64 | 94.10 | 345.70 |
128 | 177.00 | 848.20 |
- Model: Xenova/all-MiniLM-L6-v2
- Tests run: WebGPU (fp16), WebGPU (fp32)
- Sequence length: 512
- Browser: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36
- GPU: vendor=nvidia, architecture=lovelace, device=, description=