rocMLIR Weekly Sync 2025-01-19

[github-actions]

Update rocMLIR version

• Updated with changes from 2025-01-19
• Auto-generated by create-pull-request
• Update requirements.txt to rocMLIR@9bffae0f4929e14d4d269af4af19e7d0482dd67a

[github-actions]

model	DEFAULT	MLIR_EXTENDED
bert-mrpc-onnx	✅	🔴
bert-mrpc-tf	✅	✅
pytorch-examples-wlang-gru	✅	✅
pytorch-examples-wlang-lstm	✅	✅
torchvision-resnet50_1	✅	✅
cadene-dpn92_1	✅	✅
cadene-resnext101_1	✅	✅
dlrm-criteoterabyte	✅	✅
agentmodel	✅	✅
unet	✅	🔴
resnet50v1	✅	✅
bert_base_cased_fp16	✅	✅
bert_large_uncased_fp16	🔴	🔴
bert_large	✅	🔴
yolov5s	✅	✅
tinyllama	✅	✅
vicuna-fastchat	✅	✅
whisper-tiny-encoder	✅	🔴
whisper-tiny-decoder	✅	✅
distilgpt2_fp16	✅	✅

✅ - within tolerance
🔴 - not within tolerance
❌ - error in execution

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 92.29%. Comparing base (8389304) to head (a3ff9f6).

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3769   +/-   ##
========================================
  Coverage    92.29%   92.29%           
========================================
  Files          519      519           
  Lines        22217    22217           
========================================
  Hits         20505    20505           
  Misses        1712     1712           

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

[migraphx-bot]

Test	Batch	Rate new 46f892	Rate old 43488c	Diff	Compare
torchvision-resnet50	64	3,225.20	3,254.25	-0.89%	✅
torchvision-resnet50_fp16	64	6,935.12	6,916.65	0.27%	✅
torchvision-densenet121	32	2,445.90	2,455.95	-0.41%	✅
torchvision-densenet121_fp16	32	4,198.16	4,183.26	0.36%	✅
torchvision-inceptionv3	32	1,618.71	1,629.97	-0.69%	✅
torchvision-inceptionv3_fp16	32	2,700.44	2,715.98	-0.57%	✅
cadene-inceptionv4	16	754.49	762.93	-1.11%	✅
cadene-resnext64x4	16	799.19	812.98	-1.70%	✅
slim-mobilenet	64	7,035.14	7,459.33	-5.69%	🔴
slim-nasnetalarge	64	203.70	208.65	-2.37%	✅
slim-resnet50v2	64	3,415.14	3,445.08	-0.87%	✅
bert-mrpc-onnx	8	1,130.71	1,147.48	-1.46%	✅
bert-mrpc-tf	1	474.84	481.97	-1.48%	✅
pytorch-examples-wlang-gru	1	473.30	478.37	-1.06%	✅
pytorch-examples-wlang-lstm	1	447.25	439.41	1.78%	✅
torchvision-resnet50_1	1	783.04	803.28	-2.52%	✅
cadene-dpn92_1	1	425.42	427.49	-0.48%	✅
cadene-resnext101_1	1	384.01	376.23	2.07%	✅
onnx-taau-downsample	1	373.51	373.50	0.00%	✅
dlrm-criteoterabyte	1	32.54	33.31	-2.32%	✅
dlrm-criteoterabyte_fp16	1	51.07	52.64	-2.97%	✅
agentmodel	1	8,655.61	8,546.35	1.28%	✅
unet_fp16	2	57.92	58.43	-0.86%	✅
resnet50v1_fp16	1	1,034.66	1,033.48	0.11%	✅
resnet50v1_int8	1	781.91	1,018.13	-23.20%	🔴
bert_base_cased_fp16	64	1,172.96	1,181.00	-0.68%	✅
bert_large_uncased_fp16	32	362.48	365.36	-0.79%	✅
bert_large_fp16	1	200.03	201.35	-0.66%	✅
distilgpt2_fp16	16	2,214.11	2,228.65	-0.65%	✅
yolov5s	1	514.94	527.51	-2.38%	✅
tinyllama	1	43.61	43.62	-0.02%	✅
vicuna-fastchat	1	176.50	173.15	1.94%	✅
whisper-tiny-encoder	1	405.91	416.80	-2.61%	✅
whisper-tiny-decoder	1	402.44	429.87	-6.38%	🔴

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