⚡ WebGPU Benchmark Results (102.37x speedup)
#92
by
Xenova
HF staff
- opened
| Batch Size | WASM (fp32) | WebGPU (fp16) |
| 1 | 2129.10 | 218.40 |
| 2 | 4250.40 | 194.90 |
| 4 | 8532.90 | 278.20 |
| 8 | 16926.90 | 302.10 |
| 16 | 33195.90 | 466.30 |
| 32 | 66461.00 | 649.20 |
- Model: Snowflake/snowflake-arctic-embed-s
- Tests run: WASM (fp32), WebGPU (fp16)
- Sequence length: 512
- Browser: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36
- GPU: vendor=nvidia, architecture=turing, device=, description=