Fix FP8 test case

[umangyadav]

Fixes #3199

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.16%. Comparing base (e2d6efb) to head (79eb929).
Report is 150 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3243   +/-   ##
========================================
  Coverage    92.16%   92.16%           
========================================
  Files          493      493           
  Lines        19690    19690           
========================================
  Hits         18148    18148           
  Misses        1542     1542           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[ahsan-ca]

Thanks for fixing this.

[migraphx-bot]

Test	Batch	Rate new 79eb92	Rate old 497c27	Diff	Compare
torchvision-resnet50	64	1,749.54	1,748.90	0.04%	✅
torchvision-resnet50_fp16	64	4,079.21	4,080.75	-0.04%	✅
torchvision-densenet121	32	1,468.60	1,467.80	0.05%	✅
torchvision-densenet121_fp16	32	2,517.35	2,527.69	-0.41%	✅
torchvision-inceptionv3	32	888.97	888.98	-0.00%	✅
torchvision-inceptionv3_fp16	32	1,483.36	1,484.24	-0.06%	✅
cadene-inceptionv4	16	411.76	412.13	-0.09%	✅
cadene-resnext64x4	16	419.27	419.33	-0.01%	✅
slim-mobilenet	64	4,004.81	4,004.86	-0.00%	✅
slim-nasnetalarge	64	100.96	100.96	-0.01%	✅
slim-resnet50v2	64	1,679.27	1,678.94	0.02%	✅
bert-mrpc-onnx	8	616.31	616.38	-0.01%	✅
bert-mrpc-tf	1	279.59	279.52	0.02%	✅
pytorch-examples-wlang-gru	1	322.72	326.38	-1.12%	✅
pytorch-examples-wlang-lstm	1	292.88	294.48	-0.54%	✅
torchvision-resnet50_1	1	472.18	472.05	0.03%	✅
cadene-dpn92_1	1	247.59	246.45	0.46%	✅
cadene-resnext101_1	1	199.21	203.78	-2.24%	✅
onnx-taau-downsample	1	206.06	206.10	-0.02%	✅
dlrm-criteoterabyte	1	22.90	22.90	-0.01%	✅
dlrm-criteoterabyte_fp16	1	42.72	42.66	0.12%	✅
agentmodel	1	6,345.02	7,432.29	-14.63%	🔴
unet_fp16	2	34.28	34.31	-0.07%	✅
resnet50v1_fp16	1	596.88	578.62	3.16%	🔆
resnet50v1_int8	1	566.12	577.30	-1.94%	✅
bert_base_cased_fp16	64	645.63	645.72	-0.01%	✅
bert_large_uncased_fp16	32	198.82	198.85	-0.02%	✅
bert_large_fp16	1	117.08	117.34	-0.22%	✅
distilgpt2_fp16	16	1,211.42	1,210.51	0.08%	✅
yolov5s	1	301.99	293.94	2.74%	✅
tinyllama	1	23.31	23.30	0.03%	✅
vicuna-fastchat	1	133.71	133.83	-0.09%	✅
whisper-tiny-encoder	1	244.47	243.92	0.22%	✅
whisper-tiny-decoder	1	255.84	256.31	-0.18%	✅

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     ✅ bert-mrpc-tf: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

     ✅ unet: PASSED: MIGraphX meets tolerance

     ✅ resnet50v1: PASSED: MIGraphX meets tolerance

     ✅ bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

     ✅ bert_large: PASSED: MIGraphX meets tolerance

     ✅ yolov5s: PASSED: MIGraphX meets tolerance

     ✅ tinyllama: PASSED: MIGraphX meets tolerance

     ✅ vicuna-fastchat: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance