Skip to content
Blossom-CI

The inference speed of the int8 quantization version of SDXL is much slower than that of fp16 #4323

Sign in to view logs

The inference speed of the int8 quantization version of SDXL is much slower than that of fp16

The inference speed of the int8 quantization version of SDXL is much slower than that of fp16 #4323

The logs for this run have expired and are no longer available.