Update hipblaslt_supported function to reflect hipblaslt supported architectures

[ahsan-ca]

Update the architectures to accurately reflect architectures that support hipblaslt.

[ahsan-ca]

From hipblaslt:
Required hardware:
gfx90a card
gfx94x card
gfx110x card

[ahsan-ca]

To Do: confirm if gfx90a is covered by device_name >= "gfx908". Remove not starts_with(device_name, "gfx10".

[causten]

https://github.com/ROCm/hipBLASLt?tab=readme-ov-file#requirements

• lists the supported HW

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.16%. Comparing base (04ac9fc) to head (af78270).
Report is 139 commits behind head on develop.

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3544      +/-   ##
===========================================
- Coverage    92.17%   92.16%   -0.02%     
===========================================
  Files          512      512              
  Lines        21393    21401       +8     
===========================================
+ Hits         19720    19724       +4     
- Misses        1673     1677       +4     

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

[migraphx-bot]

Test	Batch	Rate new af7827	Rate old b73def	Diff	Compare
torchvision-resnet50	64	3,260.10	3,257.93	0.07%	✅
torchvision-resnet50_fp16	64	6,988.32	6,992.99	-0.07%	✅
torchvision-densenet121	32	2,436.67	2,432.26	0.18%	✅
torchvision-densenet121_fp16	32	4,084.94	4,038.39	1.15%	✅
torchvision-inceptionv3	32	1,639.24	1,638.89	0.02%	✅
torchvision-inceptionv3_fp16	32	2,764.22	2,761.69	0.09%	✅
cadene-inceptionv4	16	776.35	776.39	-0.01%	✅
cadene-resnext64x4	16	811.69	811.37	0.04%	✅
slim-mobilenet	64	7,536.37	7,532.73	0.05%	✅
slim-nasnetalarge	64	211.51	211.42	0.04%	✅
slim-resnet50v2	64	3,503.03	3,507.25	-0.12%	✅
bert-mrpc-onnx	8	1,146.86	1,147.76	-0.08%	✅
bert-mrpc-tf	1	469.43	469.91	-0.10%	✅
pytorch-examples-wlang-gru	1	412.23	514.96	-19.95%	🔴
pytorch-examples-wlang-lstm	1	383.67	386.61	-0.76%	✅
torchvision-resnet50_1	1	770.37	772.05	-0.22%	✅
cadene-dpn92_1	1	408.52	398.73	2.45%	✅
cadene-resnext101_1	1	384.27	383.67	0.16%	✅
onnx-taau-downsample	1	342.76	342.33	0.13%	✅
dlrm-criteoterabyte	1	33.33	33.33	0.00%	✅
dlrm-criteoterabyte_fp16	1	52.73	52.70	0.04%	✅
agentmodel	1	8,355.68	8,056.20	3.72%	🔆
unet_fp16	2	58.90	58.92	-0.04%	✅
resnet50v1_fp16	1	951.23	950.32	0.10%	✅
resnet50v1_int8	1	1,027.69	1,000.02	2.77%	✅
bert_base_cased_fp16	64	1,170.28	1,169.24	0.09%	✅
bert_large_uncased_fp16	32	363.50	363.69	-0.05%	✅
bert_large_fp16	1	200.06	198.89	0.59%	✅
distilgpt2_fp16	16	2,199.93	2,203.09	-0.14%	✅
yolov5s	1	535.85	540.85	-0.93%	✅
tinyllama	1	43.45	43.43	0.04%	✅
vicuna-fastchat	1	174.55	170.64	2.29%	✅
whisper-tiny-encoder	1	417.96	418.21	-0.06%	✅
whisper-tiny-decoder	1	433.58	426.10	1.75%	✅

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