Add support for MatMulNBits

[music-dino]

Resolves https://github.com/migraphx-benchmark/AMDMIGraphX/issues/193

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 98.52941% with 1 line in your changes missing coverage. Please review.

Project coverage is 92.04%. Comparing base (e2e9219) to head (ffc5304). Report is 6 commits behind head on develop.

Files with missing lines	Patch %	Lines
src/onnx/parse_matmulnbits.cpp	98.52%	1 Missing :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## develop #3496 +/- ## =========================================== + Coverage 92.02% 92.04% +0.02% =========================================== Files 509 510 +1 Lines 21005 21073 +68 =========================================== + Hits 19330 19397 +67 - Misses 1675 1676 +1 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[migraphx-bot]

Test	Batch	Rate new ffc530	Rate old e2e921	Diff	Compare
torchvision-resnet50	64	3,259.98	3,255.97	0.12%	:white_check_mark:
torchvision-resnet50_fp16	64	6,967.09	6,971.30	-0.06%	:white_check_mark:
torchvision-densenet121	32	2,432.55	2,431.20	0.06%	:white_check_mark:
torchvision-densenet121_fp16	32	4,098.34	4,087.45	0.27%	:white_check_mark:
torchvision-inceptionv3	32	1,637.25	1,635.71	0.09%	:white_check_mark:
torchvision-inceptionv3_fp16	32	2,753.28	2,755.82	-0.09%	:white_check_mark:
cadene-inceptionv4	16	780.20	780.33	-0.02%	:white_check_mark:
cadene-resnext64x4	16	808.00	806.94	0.13%	:white_check_mark:
slim-mobilenet	64	7,468.23	7,464.88	0.04%	:white_check_mark:
slim-nasnetalarge	64	208.42	208.51	-0.04%	:white_check_mark:
slim-resnet50v2	64	3,439.94	3,435.02	0.14%	:white_check_mark:
bert-mrpc-onnx	8	1,146.28	1,146.59	-0.03%	:white_check_mark:
bert-mrpc-tf	1	320.26	318.44	0.57%	:white_check_mark:
pytorch-examples-wlang-gru	1	385.11	421.02	-8.53%	:red_circle:
pytorch-examples-wlang-lstm	1	381.64	374.33	1.95%	:white_check_mark:
torchvision-resnet50_1	1	767.07	803.63	-4.55%	:red_circle:
cadene-dpn92_1	1	396.42	395.85	0.15%	:white_check_mark:
cadene-resnext101_1	1	371.70	379.14	-1.96%	:white_check_mark:
onnx-taau-downsample	1	366.21	366.52	-0.09%	:white_check_mark:
dlrm-criteoterabyte	1	35.03	35.01	0.04%	:white_check_mark:
dlrm-criteoterabyte_fp16	1	58.17	58.19	-0.03%	:white_check_mark:
agentmodel	1	8,135.64	8,063.61	0.89%	:white_check_mark:
unet_fp16	2	59.03	58.95	0.14%	:white_check_mark:
resnet50v1_fp16	1	906.46	950.25	-4.61%	:red_circle:
resnet50v1_int8	1	979.66	971.97	0.79%	:white_check_mark:
bert_base_cased_fp16	64	1,171.44	1,170.73	0.06%	:white_check_mark:
bert_large_uncased_fp16	32	363.68	363.46	0.06%	:white_check_mark:
bert_large_fp16	1	211.40	213.45	-0.96%	:white_check_mark:
distilgpt2_fp16	16	2,204.69	2,199.49	0.24%	:white_check_mark:
yolov5s	1	547.73	539.25	1.57%	:white_check_mark:
tinyllama	1	43.46	43.47	-0.03%	:white_check_mark:
vicuna-fastchat	1	170.22	174.86	-2.65%	:white_check_mark:
whisper-tiny-encoder	1	418.13	417.66	0.11%	:white_check_mark:
whisper-tiny-decoder	1	427.72	427.92	-0.05%	:white_check_mark:

This build is not recommended to merge :red_circle:

[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: cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     :white_check_mark: cadene-resnext101_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

     :white_check_mark: bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

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

     :white_check_mark: bert_large: PASSED: MIGraphX meets tolerance

     :white_check_mark: yolov5s: PASSED: MIGraphX meets tolerance

     :white_check_mark: tinyllama: PASSED: MIGraphX meets tolerance

     :white_check_mark: vicuna-fastchat: PASSED: MIGraphX meets tolerance

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

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

     :white_check_mark: distilgpt2_fp16: PASSED: MIGraphX meets tolerance

[TedThemistokleous]

Odd CI is all green but here its showing it didn't run. Rekicked this as I don't think this update is showing up on github.

[music-dino]

Overall looks alright. Will see what CI says in the morning. Just another question I have about how you handle blob_sizes.

There's a clang_debug failure, but I can't access the logs.

[TedThemistokleous]

Overall looks alright. Will see what CI says in the morning. Just another question I have about how you handle blob_sizes.

There's a clang_debug failure, but I can't access the logs.

Looks clean from my end. Dont worry about it.