Onnxruntime Weekly Sync 2026-08-21

[github-actions]

Update CI point for Onnxruntime builds

• Updated with changes from 2026-08-21
• Auto-generated by create-pull-request
• Update .onnxrt-commit to a88c1168cab0a8c64c2baf17aa9ba0dcca595cfc

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

Test	Batch	New Rate (6100e0)	Old Rate (3a503c)*	Diff	Status
torchvision-resnet50	64	3,298.07	3,264.92	1.02%	✅
torchvision-resnet50_fp16	64	7,882.72	7,548.67	4.43%	✅
torchvision-densenet121	32	2,490.74	2,483.99	0.27%	✅
torchvision-densenet121_fp16	32	5,016.25	5,004.24	0.24%	✅
torchvision-inceptionv3	32	2,058.90	2,058.51	0.02%	✅
torchvision-inceptionv3_fp16	32	4,450.82	4,416.99	0.77%	✅
cadene-inceptionv4	16	817.67	820.61	-0.36%	✅
cadene-resnext64x4	16	785.16	782.78	0.30%	✅
slim-mobilenet	64	8,372.50	8,386.36	-0.17%	✅
slim-nasnetalarge	64	229.24	228.86	0.17%	✅
slim-resnet50v2	64	3,228.05	3,180.91	1.48%	✅
bert-mrpc-onnx	8	1,169.33	1,168.84	0.04%	✅
bert-mrpc-tf	1	502.73	498.63	0.82%	✅
pytorch-examples-wlang-gru	1	421.36	473.35	-10.98%	🔴
pytorch-examples-wlang-lstm	1	554.89	384.83	44.19%	🔆
torchvision-resnet50_1	1	1,050.53	1,046.63	0.37%	✅
cadene-dpn92_1	1	457.13	437.32	4.53%	✅
cadene-resnext101_1	1	364.35	365.89	-0.42%	✅
onnx-taau-downsample	1	848.96	844.09	0.58%	✅
dlrm-criteoterabyte	1	32.23	32.42	-0.59%	✅
dlrm-criteoterabyte_fp16	1	51.47	51.80	-0.64%	✅
agentmodel	1	14,001.25	9,209.12	52.04%	🔆
unet_fp16	2	58.37	58.80	-0.73%	✅
resnet50v1_fp16	1	1,444.75	1,366.11	5.76%	🔆
resnet50v1_int8	1	1,731.20	1,883.96	-8.11%	🔴
bert_base_cased_fp16	64	1,099.20	1,098.16	0.09%	✅
bert_large_uncased_fp16	32	347.20	345.59	0.47%	✅
bert_large_fp16	1	206.59	206.59	0.00%	✅
distilgpt2_fp16	16	2,102.97	2,092.89	0.48%	✅
yolov5s	1	566.28	558.33	1.42%	✅
tinyllama	1	45.79	45.83	-0.10%	✅
vicuna-fastchat	1	44.14	44.20	-0.14%	✅
whisper-tiny-encoder	1	412.74	411.87	0.21%	✅
whisper-tiny-decoder	1	409.63	408.48	0.28%	✅
llama2_7b	1	20.85	20.84	0.07%	✅
qwen1.5-7b	1	23.66	23.58	0.32%	✅
phi3-3.8b	1	28.35	26.72	6.13%	🔆
llama3-8b	1	22.72	21.80	4.22%	✅
whisper-large-encoder	1	10.16	10.18	-0.13%	✅
whisper-large-decoder	1	107.01	105.30	1.62%	✅
mistral-7b	1	23.76	23.78	-0.06%	✅
FLUX.1-schnell	1	785.47	755.22	4.01%	✅

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	❌	ERROR - check error output traceback Traceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 377, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 313, in main import tensorflow as tf File "/usr/local/lib/python3.12/dist-packages/tensorflow/init.py", line 40, in from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow # pylint: disable=unused-import ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 37, in self_check.preload_check() File "/usr/local/lib/python3.12/dist-packages/tensorflow/python/platform/self_check.py", line 63, in preload_check from tensorflow.python.platform import _pywrap_cpu_feature_guard ImportError: libnuma.so.1: cannot open shared object file: No such file or directory
pytorch-examples-wlang-gru	🔴	FAILED: MIGraphX is not within tolerance - check verbose output
pytorch-examples-wlang-lstm	🔴	FAILED: MIGraphX is not within tolerance - check verbose output
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	🔴	FAILED: MIGraphX is not within tolerance - check verbose output
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