parse onnx graph for int4

[lakhinderwalia]

No description provided.

[codecov]

Codecov Report

Attention: Patch coverage is 60.86957% with 9 lines in your changes missing coverage. Please review.

Project coverage is 92.12%. Comparing base (51a24d8) to head (221444d).
Report is 10 commits behind head on develop.

Files with missing lines	Patch %	Lines
src/onnx/onnx_parser.cpp	60.86%	9 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3408      +/-   ##
===========================================
- Coverage    92.16%   92.12%   -0.04%     
===========================================
  Files          504      504              
  Lines        20486    20504      +18     
===========================================
+ Hits         18880    18889       +9     
- Misses        1606     1615       +9     

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

[migraphx-bot]

Test	Batch	Rate new 221444	Rate old e583e7	Diff	Compare
torchvision-resnet50	64	3,254.05	3,250.33	0.11%	✅
torchvision-resnet50_fp16	64	6,988.64	6,992.29	-0.05%	✅
torchvision-densenet121	32	2,435.61	2,433.11	0.10%	✅
torchvision-densenet121_fp16	32	4,107.85	4,103.85	0.10%	✅
torchvision-inceptionv3	32	1,635.87	1,635.59	0.02%	✅
torchvision-inceptionv3_fp16	32	2,745.34	2,740.97	0.16%	✅
cadene-inceptionv4	16	776.83	776.60	0.03%	✅
cadene-resnext64x4	16	808.76	808.06	0.09%	✅
slim-mobilenet	64	7,460.86	7,457.10	0.05%	✅
slim-nasnetalarge	64	207.94	207.88	0.03%	✅
slim-resnet50v2	64	3,345.99	3,343.78	0.07%	✅
bert-mrpc-onnx	8	1,152.22	1,151.31	0.08%	✅
bert-mrpc-tf	1	309.97	311.19	-0.39%	✅
pytorch-examples-wlang-gru	1	420.38	424.43	-0.95%	✅
pytorch-examples-wlang-lstm	1	384.78	377.46	1.94%	✅
torchvision-resnet50_1	1	815.30	812.29	0.37%	✅
cadene-dpn92_1	1	434.80	435.71	-0.21%	✅
cadene-resnext101_1	1	383.27	383.82	-0.14%	✅
onnx-taau-downsample	1	345.18	344.50	0.20%	✅
dlrm-criteoterabyte	1	35.03	35.09	-0.17%	✅
dlrm-criteoterabyte_fp16	1	58.10	58.05	0.07%	✅
agentmodel	1	9,857.36	7,873.33	25.20%	🔆
unet_fp16	2	57.95	58.01	-0.11%	✅
resnet50v1_fp16	1	896.24	917.06	-2.27%	✅
resnet50v1_int8	1	933.62	920.98	1.37%	✅
bert_base_cased_fp16	64	1,154.67	1,151.61	0.27%	✅
bert_large_uncased_fp16	32	355.99	355.61	0.11%	✅
bert_large_fp16	1	212.09	210.45	0.78%	✅
distilgpt2_fp16	16	2,164.73	2,156.95	0.36%	✅
yolov5s	1	537.59	535.99	0.30%	✅
tinyllama	1	43.50	43.42	0.19%	✅
vicuna-fastchat	1	177.31	174.03	1.88%	✅
whisper-tiny-encoder	1	409.61	406.71	0.71%	✅
whisper-tiny-decoder	1	434.12	425.82	1.95%	✅

Check results before 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

[pfultz2]

There are still tidy fixes needed for this PR, it shouldn't be merged in yet. @causten