[MIGraphX EP Support]Add rocm to transformers/benchmark.py script (#22299)

### Description
Add ROCm EP option to benchmark.py script when using int8 quantization.



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
Without this change benchmarks with int8 quantization cannot be run with
ROCm execution provider.
This commit is contained in:
stsokolo 2024-10-08 06:57:18 +02:00 committed by GitHub
parent 407c1ab2e2
commit efb8703a25
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -787,7 +787,7 @@ def main():
logger.error("fp16 is for GPU only")
return
if args.precision == Precision.INT8 and args.use_gpu and args.provider != "migraphx":
if args.precision == Precision.INT8 and args.use_gpu and args.provider not in ["migraphx", "rocm"]:
logger.error("int8 is for CPU only")
return