⚡ WebGPU Benchmark Results (32.58x speedup)
#10
by
Xenova
- opened
| Batch Size | WASM (ms) | WebGPU (ms) |
| 1 | 508.30 | 45.60 |
| 2 | 1053.90 | 206.80 |
| 4 | 2090.20 | 58.40 |
| 8 | 4129.10 | 313.10 |
| 16 | 8228.20 | 406.80 |
| 32 | 16394.80 | 503.20 |
- Model: Xenova/all-MiniLM-L6-v2
- Quantized: false
- Sequence length: 512
- Browser: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36
- GPU: vendor=nvidia, architecture=turing, device=, description=