⚡ WebGPU Benchmark Results (25.98x speedup)
#9
by
Xenova
HF staff
- opened
| Batch Size | WASM (ms) | WebGPU (ms) |
| 1 | 509.50 | 12.60 |
| 2 | 1064.90 | 140.80 |
| 4 | 2090.80 | 59.20 |
| 8 | 4142.40 | 262.50 |
| 16 | 8235.90 | 467.40 |
| 32 | 16392.30 | 630.90 |
- 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=