Update onnx.proto for int4

[lakhinderwalia]

Update onnx.proto from https://github.com/onnx/onnx/blob/main/onnx/onnx.proto

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.26%. Comparing base (ae2b026) to head (072e762).
Report is 9 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3373   +/-   ##
========================================
  Coverage    92.26%   92.26%           
========================================
  Files          500      500           
  Lines        20057    20057           
========================================
  Hits         18506    18506           
  Misses        1551     1551           

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

[migraphx-bot]

Test	Batch	Rate new 83e6bc	Rate old ae2b02	Diff	Compare
torchvision-resnet50	64	3,233.56	3,238.75	-0.16%	✅
torchvision-resnet50_fp16	64	6,878.44	6,883.54	-0.07%	✅
torchvision-densenet121	32	2,427.24	2,428.82	-0.07%	✅
torchvision-densenet121_fp16	32	4,083.85	4,068.52	0.38%	✅
torchvision-inceptionv3	32	1,636.13	1,636.23	-0.01%	✅
torchvision-inceptionv3_fp16	32	2,741.84	2,742.33	-0.02%	✅
cadene-inceptionv4	16	770.19	771.15	-0.12%	✅
cadene-resnext64x4	16	802.99	804.10	-0.14%	✅
slim-mobilenet	64	7,440.37	7,439.62	0.01%	✅
slim-nasnetalarge	64	207.61	207.57	0.02%	✅
slim-resnet50v2	64	3,342.70	3,344.87	-0.06%	✅
bert-mrpc-onnx	8	1,150.04	1,147.91	0.19%	✅
bert-mrpc-tf	1	311.78	311.51	0.09%	✅
pytorch-examples-wlang-gru	1	420.90	421.75	-0.20%	✅
pytorch-examples-wlang-lstm	1	377.99	384.10	-1.59%	✅
torchvision-resnet50_1	1	806.62	748.32	7.79%	🔆
cadene-dpn92_1	1	432.40	433.18	-0.18%	✅
cadene-resnext101_1	1	378.16	380.63	-0.65%	✅
onnx-taau-downsample	1	344.81	344.74	0.02%	✅
dlrm-criteoterabyte	1	35.03	35.07	-0.11%	✅
dlrm-criteoterabyte_fp16	1	57.28	57.29	-0.03%	✅
agentmodel	1	9,819.23	7,926.38	23.88%	🔆
unet_fp16	2	57.79	57.69	0.16%	✅
resnet50v1_fp16	1	934.91	946.41	-1.21%	✅
resnet50v1_int8	1	938.67	943.78	-0.54%	✅
bert_base_cased_fp16	64	1,141.51	1,142.08	-0.05%	✅
bert_large_uncased_fp16	32	353.68	351.75	0.55%	✅
bert_large_fp16	1	208.12	211.73	-1.70%	✅
distilgpt2_fp16	16	2,154.86	2,153.52	0.06%	✅
yolov5s	1	492.58	501.78	-1.83%	✅
tinyllama	1	43.35	43.42	-0.15%	✅
vicuna-fastchat	1	175.80	171.05	2.77%	✅
whisper-tiny-encoder	1	410.61	412.65	-0.49%	✅
whisper-tiny-decoder	1	427.57	429.35	-0.41%	✅

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

[causten]

@lakhinderwalia please fix the format failure

[kahmed10]

@lakhinderwalia please fix the format failure

We should be ignoring this file since it's coming from onnx.

[lakhinderwalia]

@lakhinderwalia please fix the format failure

We should be ignoring this file since it's coming from onnx.

Added an exception for this file name -- logically speaking this file should already be ignored by the existing rules for examining diffs. Not sure if this will actually fix the root cause here.

[pfultz2]

Exception didnt work. @causten we should just merge it in. Since the format is done on a diff this wont affect other PRs.