Enable attention by default on mi300

[pfultz2]

No description provided.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.04%. Comparing base (1f4bc99) to head (c91dfae).

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3463   +/-   ##
========================================
  Coverage    92.04%   92.04%           
========================================
  Files          506      506           
  Lines        20864    20864           
========================================
  Hits         19204    19204           
  Misses        1660     1660           

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

[migraphx-bot]

Test	Batch	Rate new bd75c3	Rate old bdbe34	Diff	Compare
torchvision-resnet50	64	3,260.60	3,258.84	0.05%	✅
torchvision-resnet50_fp16	64	6,986.08	6,981.91	0.06%	✅
torchvision-densenet121	32	2,436.11	2,436.52	-0.02%	✅
torchvision-densenet121_fp16	32	4,091.44	4,070.78	0.51%	✅
torchvision-inceptionv3	32	1,637.47	1,640.50	-0.18%	✅
torchvision-inceptionv3_fp16	32	2,763.58	2,764.39	-0.03%	✅
cadene-inceptionv4	16	776.24	777.25	-0.13%	✅
cadene-resnext64x4	16	809.26	809.84	-0.07%	✅
slim-mobilenet	64	7,537.56	7,537.85	-0.00%	✅
slim-nasnetalarge	64	211.85	211.79	0.03%	✅
slim-resnet50v2	64	3,506.35	3,504.89	0.04%	✅
bert-mrpc-onnx	8	1,151.61	1,152.66	-0.09%	✅
bert-mrpc-tf	1	465.87	463.93	0.42%	✅
pytorch-examples-wlang-gru	1	424.44	485.39	-12.56%	🔴
pytorch-examples-wlang-lstm	1	396.66	384.58	3.14%	🔆
torchvision-resnet50_1	1	777.40	817.62	-4.92%	🔴
cadene-dpn92_1	1	400.29	399.06	0.31%	✅
cadene-resnext101_1	1	382.14	382.30	-0.04%	✅
onnx-taau-downsample	1	343.06	343.08	-0.01%	✅
dlrm-criteoterabyte	1	33.34	33.33	0.01%	✅
dlrm-criteoterabyte_fp16	1	52.75	52.74	0.02%	✅
agentmodel	1	8,320.51	8,377.88	-0.68%	✅
unet_fp16	2	58.97	58.79	0.31%	✅
resnet50v1_fp16	1	958.02	937.71	2.17%	✅
resnet50v1_int8	1	972.61	1,041.29	-6.60%	🔴
bert_base_cased_fp16	64	1,170.56	1,170.74	-0.02%	✅
bert_large_uncased_fp16	32	363.53	363.58	-0.01%	✅
bert_large_fp16	1	198.80	199.03	-0.12%	✅
distilgpt2_fp16	16	2,199.43	2,199.30	0.01%	✅
yolov5s	1	539.03	540.42	-0.26%	✅
tinyllama	1	43.48	43.45	0.07%	✅
vicuna-fastchat	1	173.34	169.65	2.18%	✅
whisper-tiny-encoder	1	418.67	418.63	0.01%	✅
whisper-tiny-decoder	1	427.87	430.21	-0.54%	✅

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