⚡ WebGPU Benchmark Results (75.82x speedup) | Snowflake/snowflake-arctic-embed-xs (fp16) | M3 Max
#102
by
do-me
- opened
| Batch Size | WASM (fp16) | WebGPU (fp16) |
| 1 | 307.10 | 16.10 |
| 2 | 600.30 | 22.10 |
| 4 | 1212.10 | 34.00 |
| 8 | 2472.80 | 49.70 |
| 16 | 5086.10 | 87.80 |
| 32 | 10509.20 | 138.60 |
- Model: Snowflake/snowflake-arctic-embed-xs
- Tests run: WASM (fp16), WebGPU (fp16)
- Sequence length: 512
- Browser: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36
- GPU: vendor=apple, architecture=common-3, device=, description=