Fix exception raised for quantization block-size = 1 in quark-generated int4 models.

[lakhinderwalia]

This PR fixes an exception that was raised while parsing for block quantization: block size = 1.
This corner case is raising an exception in quark-generated int-4 graphs.
A test case has been created to verify that no exception is raised, using a snippet off the quark generated model.

(Additionally, a test is being moved, based on a prior PR feedback. This test has nothing to do with this exception.)

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.05%. Comparing base (b923336) to head (520ce0d).
Report is 6 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3510      +/-   ##
===========================================
+ Coverage    92.02%   92.05%   +0.02%     
===========================================
  Files          509      509              
  Lines        21014    21014              
===========================================
+ Hits         19339    19345       +6     
+ Misses        1675     1669       -6     

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

[migraphx-bot]

Test	Batch	Rate new 520ce0	Rate old b92333	Diff	Compare
torchvision-resnet50	64	3,261.36	3,263.77	-0.07%	✅
torchvision-resnet50_fp16	64	6,994.55	6,996.15	-0.02%	✅
torchvision-densenet121	32	2,432.85	2,432.72	0.01%	✅
torchvision-densenet121_fp16	32	4,093.37	4,082.35	0.27%	✅
torchvision-inceptionv3	32	1,638.18	1,637.26	0.06%	✅
torchvision-inceptionv3_fp16	32	2,764.91	2,763.65	0.05%	✅
cadene-inceptionv4	16	776.22	775.75	0.06%	✅
cadene-resnext64x4	16	808.87	808.46	0.05%	✅
slim-mobilenet	64	7,531.01	7,531.96	-0.01%	✅
slim-nasnetalarge	64	211.41	211.47	-0.03%	✅
slim-resnet50v2	64	3,499.64	3,502.05	-0.07%	✅
bert-mrpc-onnx	8	1,150.24	1,151.10	-0.07%	✅
bert-mrpc-tf	1	465.58	489.88	-4.96%	🔴
pytorch-examples-wlang-gru	1	416.56	426.32	-2.29%	✅
pytorch-examples-wlang-lstm	1	393.65	367.19	7.21%	🔆
torchvision-resnet50_1	1	823.25	822.42	0.10%	✅
cadene-dpn92_1	1	401.99	410.84	-2.15%	✅
cadene-resnext101_1	1	383.53	381.55	0.52%	✅
onnx-taau-downsample	1	342.36	343.34	-0.29%	✅
dlrm-criteoterabyte	1	33.33	33.37	-0.13%	✅
dlrm-criteoterabyte_fp16	1	52.75	52.75	-0.01%	✅
agentmodel	1	9,697.91	8,588.85	12.91%	🔆
unet_fp16	2	58.80	58.84	-0.07%	✅
resnet50v1_fp16	1	998.58	922.91	8.20%	🔆
resnet50v1_int8	1	1,003.29	969.45	3.49%	🔆
bert_base_cased_fp16	64	1,171.90	1,170.56	0.11%	✅
bert_large_uncased_fp16	32	363.39	363.70	-0.09%	✅
bert_large_fp16	1	198.76	200.51	-0.87%	✅
distilgpt2_fp16	16	2,200.83	2,200.62	0.01%	✅
yolov5s	1	544.08	546.87	-0.51%	✅
tinyllama	1	43.46	43.49	-0.06%	✅
vicuna-fastchat	1	172.42	170.79	0.95%	✅
whisper-tiny-encoder	1	418.15	419.48	-0.32%	✅
whisper-tiny-decoder	1	426.65	435.90	-2.12%	✅

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