Onnxruntime Weekly Sync 2026-07-31

[github-actions]

Update CI point for Onnxruntime builds

• Updated with changes from 2026-07-31
• Auto-generated by create-pull-request
• Update .onnxrt-commit to b4d126e4da5031bbc5a50a9007fa3b713d17d8ab

[gh-app-migraphx-bot-pr-write]

Test	Batch	New Rate (7e04f7)	Old Rate (3a503c)*	Diff	Status
torchvision-resnet50	64	3,326.65	3,264.92	1.89%	✅
torchvision-resnet50_fp16	64	7,881.66	7,548.67	4.41%	✅
torchvision-densenet121	32	2,491.42	2,483.99	0.30%	✅
torchvision-densenet121_fp16	32	2,104.25	5,004.24	-57.95%	🔴
torchvision-inceptionv3	32	848.43	2,058.51	-58.78%	🔴
torchvision-inceptionv3_fp16	32	4,496.86	4,416.99	1.81%	✅
cadene-inceptionv4	16	821.41	820.61	0.10%	✅
cadene-resnext64x4	16	782.85	782.78	0.01%	✅
slim-mobilenet	64	8,389.61	8,386.36	0.04%	✅
slim-nasnetalarge	64	227.85	228.86	-0.44%	✅
slim-resnet50v2	64	3,237.13	3,180.91	1.77%	✅
bert-mrpc-onnx	8	1,168.12	1,168.84	-0.06%	✅
bert-mrpc-tf	1	490.59	498.63	-1.61%	✅
pytorch-examples-wlang-gru	1	477.21	473.35	0.82%	✅
pytorch-examples-wlang-lstm	1	381.73	384.83	-0.80%	✅
torchvision-resnet50_1	1	1,048.21	1,046.63	0.15%	✅
cadene-dpn92_1	1	451.14	437.32	3.16%	✅
cadene-resnext101_1	1	366.50	365.89	0.17%	✅
onnx-taau-downsample	1	846.38	844.09	0.27%	✅
dlrm-criteoterabyte	1	32.21	32.42	-0.65%	✅
dlrm-criteoterabyte_fp16	1	51.79	51.80	-0.02%	✅
agentmodel	1	9,338.29	9,209.12	1.40%	✅
unet_fp16	2	58.85	58.80	0.09%	✅
resnet50v1_fp16	1	1,427.36	1,366.11	4.48%	✅
resnet50v1_int8	1	1,711.61	1,883.96	-9.15%	🔴
bert_base_cased_fp16	64	1,099.57	1,098.16	0.13%	✅
bert_large_uncased_fp16	32	344.26	345.59	-0.39%	✅
bert_large_fp16	1	206.06	206.59	-0.26%	✅
distilgpt2_fp16	16	2,093.61	2,092.89	0.03%	✅
yolov5s	1	558.73	558.33	0.07%	✅
tinyllama	1	45.80	45.83	-0.07%	✅
vicuna-fastchat	1	44.17	44.20	-0.07%	✅
whisper-tiny-encoder	1	412.32	411.87	0.11%	✅
whisper-tiny-decoder	1	408.22	408.48	-0.06%	✅
llama2_7b	1	20.84	20.84	-0.00%	✅
qwen1.5-7b	1	23.53	23.58	-0.20%	✅
phi3-3.8b	1	26.71	26.72	-0.03%	✅
llama3-8b	1	21.68	21.80	-0.57%	✅
whisper-large-encoder	1	10.18	10.18	0.05%	✅
whisper-large-decoder	1	105.83	105.30	0.50%	✅
mistral-7b	1	23.75	23.78	-0.10%	✅
FLUX.1-schnell	1	378.37	755.22	-49.90%	🔴

Regressions detected 🔴

* No develop baseline was found for this PR's branch point; compared against the latest available develop run instead.

[gh-app-migraphx-bot-pr-write]

Test	Status	Result
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
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
llama2_7b	✅	PASSED: MIGraphX meets tolerance
qwen1.5-7b	✅	PASSED: MIGraphX meets tolerance
phi3-3.8b	✅	PASSED: MIGraphX meets tolerance
llama3-8b	✅	PASSED: MIGraphX meets tolerance
whisper-large-encoder	✅	PASSED: MIGraphX meets tolerance
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance