Run optimize_module for int8 quantization

[pfultz2]

This should improve performance and accuracy.

[codecov]

Codecov Report

Merging #2300 (518e9c9) into develop (c7f0fbc) will increase coverage by 0.00%.
Report is 6 commits behind head on develop.
The diff coverage is 100.00%.

❗ Current head 518e9c9 differs from pull request most recent head a026f6f. Consider uploading reports for the commit a026f6f to get more accurate results

@@           Coverage Diff            @@
##           develop    #2300   +/-   ##
========================================
  Coverage    91.50%   91.50%           
========================================
  Files          431      431           
  Lines        16140    16141    +1     
========================================
+ Hits         14769    14770    +1     
  Misses        1371     1371           

Files	Coverage Δ
src/quantization.cpp	86.36% <100.00%> (+0.31%)	⬆️

[migraphx-bot]

Test	Batch	Rate new c6d283	Rate old 65c37c	Diff	Compare
torchvision-resnet50	64	2,323.64	2,324.63	-0.04%	✅
torchvision-resnet50_fp16	64	5,332.53	5,357.98	-0.47%	✅
torchvision-densenet121	32	1,845.48	1,847.88	-0.13%	✅
torchvision-densenet121_fp16	32	3,417.52	3,409.96	0.22%	✅
torchvision-inceptionv3	32	1,291.14	1,296.14	-0.39%	✅
torchvision-inceptionv3_fp16	32	2,536.76	2,534.23	0.10%	✅
cadene-inceptionv4	16	619.85	620.23	-0.06%	✅
cadene-resnext64x4	16	589.67	588.45	0.21%	✅
slim-mobilenet	64	7,218.60	7,215.95	0.04%	✅
slim-nasnetalarge	64	236.36	236.51	-0.06%	✅
slim-resnet50v2	64	2,554.98	2,555.59	-0.02%	✅
bert-mrpc-onnx	8	824.66	825.02	-0.04%	✅
bert-mrpc-tf	1	389.37	389.38	-0.00%	✅
pytorch-examples-wlang-gru	1	298.11	294.47	1.24%	✅
pytorch-examples-wlang-lstm	1	315.40	307.96	2.42%	✅
torchvision-resnet50_1	1	547.76	544.78	0.55%	✅
torchvision-inceptionv3_1	1	300.34	305.19	-1.59%	✅
cadene-dpn92_1	1	356.49	352.21	1.21%	✅
cadene-resnext101_1	1	218.48	220.12	-0.74%	✅
slim-vgg16_1	1	224.10	224.29	-0.08%	✅
slim-mobilenet_1	1	1,502.17	1,497.40	0.32%	✅
slim-inceptionv4_1	1	216.44	214.96	0.69%	✅
onnx-taau-downsample	1	306.77	306.79	-0.01%	✅
dlrm-criteoterabyte	1	21.68	21.67	0.08%	✅
dlrm-criteoterabyte_fp16	1	40.65	40.71	-0.16%	✅
agentmodel	1	5,792.80	5,776.01	0.29%	✅
unet_fp16	2	55.13	55.16	-0.06%	✅
resnet50v1_fp16	1	769.82	766.51	0.43%	✅
bert_base_cased_fp16	64	970.47	971.03	-0.06%	✅
bert_large_uncased_fp16	32	304.96	305.05	-0.03%	✅
bert_large_fp16	1	166.99	166.83	0.10%	✅
distilgpt2_fp16	16	1,351.13	1,350.80	0.02%	✅

This build is OK for merge ✅

[migraphx-bot]

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

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

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

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

    :white_check_mark:torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:torchvision-inceptionv3_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:cadene-dpn92_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:cadene-resnext101_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-vgg16_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-mobilenet_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:slim-inceptionv4_1: PASSED: MIGraphX meets tolerance

    :white_check_mark:dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

    :white_check_mark:agentmodel: PASSED: MIGraphX meets tolerance

    :white_check_mark:unet: PASSED: MIGraphX meets tolerance

    :white_check_mark:resnet50v1: PASSED: MIGraphX meets tolerance

🔴bert_base_cased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

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

    :white_check_mark:bert_large: PASSED: MIGraphX meets tolerance

🔴distilgpt2_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

[TedThemistokleous]

Approving this as I believe this will effect changes on the EP side/accuracy once I start testing accuracy