⚡ WebGPU Benchmark Results (40.99x speedup) | Snowflake/snowflake-arctic-embed-s (fp32) | M3 Max
#100
by
do-me
- opened
| Batch Size | WASM (fp32) | WebGPU (fp32) |
| 1 | 576.10 | 26.10 |
| 2 | 1147.50 | 55.90 |
| 4 | 2349.20 | 71.60 |
| 8 | 4775.80 | 139.50 |
| 16 | 9647.80 | 258.70 |
| 32 | 19732.20 | 481.40 |
- Model: Snowflake/snowflake-arctic-embed-s
- Tests run: WASM (fp32), WebGPU (fp32)
- 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=