⚡ WebGPU Benchmark Results (2.13x speedup) - Windows fp16 vs. fp32

#56
by Xenova HF staff - opened
Owner
Batch SizeWebGPU (fp16)WebGPU (fp32)
111.7014.10
245.8056.10
441.1057.70
897.70133.30
16153.40215.70
32338.60722.50
  • Model: Xenova/all-MiniLM-L6-v2
  • Tests run: WebGPU (fp16), WebGPU (fp32)
  • 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=

Sign up or log in to comment