⚡ WebGPU Benchmark Results (32.32x speedup)
#38
by
omaryshchenko
- opened
| Batch Size | WASM (ms) | WebGPU (ms) |
| 1 | 470.60 | 11.20 |
| 2 | 958.00 | 46.50 |
| 4 | 1871.50 | 133.90 |
| 8 | 3652.20 | 91.50 |
| 16 | 7688.50 | 241.20 |
| 32 | 15308.80 | 473.70 |
- 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=ampere, device=, description=