⚡ WebGPU Benchmark Results (40.40x speedup)
#30
by
osanseviero
- opened
| Batch Size | WASM (ms) | WebGPU (ms) |
| 1 | 467.40 | 10.30 |
| 2 | 958.50 | 40.40 |
| 4 | 1912.10 | 222.60 |
| 8 | 3786.80 | 138.80 |
| 16 | 8407.40 | 320.60 |
| 32 | 15664.60 | 387.70 |
- Model: Xenova/all-MiniLM-L6-v2
- Quantized: false
- Sequence length: 512
- Browser: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36
- GPU: vendor=nvidia, architecture=ampere, device=, description=