Small fixes for GQA

[turneram]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.17%. Comparing base (275f854) to head (3a3707c).
Report is 134 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3537   +/-   ##
========================================
  Coverage    92.17%   92.17%           
========================================
  Files          512      512           
  Lines        21391    21391           
========================================
  Hits         19718    19718           
  Misses        1673     1673           

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

[migraphx-bot]

Test	Batch	Rate new 3a3707	Rate old 275f85	Diff	Compare
torchvision-resnet50	64	3,260.56	3,260.33	0.01%	✅
torchvision-resnet50_fp16	64	6,987.49	6,996.93	-0.13%	✅
torchvision-densenet121	32	2,435.33	2,436.13	-0.03%	✅
torchvision-densenet121_fp16	32	4,036.08	4,080.65	-1.09%	✅
torchvision-inceptionv3	32	1,639.77	1,639.01	0.05%	✅
torchvision-inceptionv3_fp16	32	2,762.50	2,759.60	0.11%	✅
cadene-inceptionv4	16	775.73	775.88	-0.02%	✅
cadene-resnext64x4	16	810.95	811.11	-0.02%	✅
slim-mobilenet	64	7,536.28	7,539.27	-0.04%	✅
slim-nasnetalarge	64	211.49	211.54	-0.03%	✅
slim-resnet50v2	64	3,507.96	3,505.47	0.07%	✅
bert-mrpc-onnx	8	1,151.43	1,151.85	-0.04%	✅
bert-mrpc-tf	1	463.74	463.50	0.05%	✅
pytorch-examples-wlang-gru	1	408.79	411.56	-0.67%	✅
pytorch-examples-wlang-lstm	1	380.17	388.27	-2.09%	✅
torchvision-resnet50_1	1	785.28	764.51	2.72%	✅
cadene-dpn92_1	1	401.12	402.09	-0.24%	✅
cadene-resnext101_1	1	373.98	381.69	-2.02%	✅
onnx-taau-downsample	1	342.68	342.54	0.04%	✅
dlrm-criteoterabyte	1	33.33	33.35	-0.06%	✅
dlrm-criteoterabyte_fp16	1	52.71	52.74	-0.07%	✅
agentmodel	1	8,016.80	8,186.92	-2.08%	✅
unet_fp16	2	58.87	58.82	0.09%	✅
resnet50v1_fp16	1	956.77	953.22	0.37%	✅
resnet50v1_int8	1	1,020.16	1,003.11	1.70%	✅
bert_base_cased_fp16	64	1,172.74	1,170.57	0.19%	✅
bert_large_uncased_fp16	32	363.54	363.63	-0.03%	✅
bert_large_fp16	1	198.76	201.70	-1.46%	✅
distilgpt2_fp16	16	2,199.66	2,202.28	-0.12%	✅
yolov5s	1	537.55	537.82	-0.05%	✅
tinyllama	1	43.40	43.44	-0.09%	✅
vicuna-fastchat	1	180.70	173.47	4.17%	🔆
whisper-tiny-encoder	1	418.62	418.26	0.09%	✅
whisper-tiny-decoder	1	428.79	436.61	-1.79%	✅

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