⚡ WebGPU Benchmark Results (43.25x speedup) - jina-embeddings-v2-small-en (fp16)
#65
by
Xenova
HF staff
- opened
| Batch Size | WASM (fp16) | WebGPU (fp16) |
| 1 | 1549.10 | 127.80 |
| 2 | 3100.80 | 255.70 |
| 4 | 6202.90 | 260.60 |
| 8 | 12378.50 | 402.80 |
| 16 | 24914.20 | 748.40 |
| 32 | 49775.00 | 1150.90 |
- Model: Xenova/jina-embeddings-v2-small-en
- Tests run: WASM (fp16), WebGPU (fp16)
- 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=