Onnxruntime Weekly Sync 2026-04-17

[github-actions]

Update CI point for Onnxruntime builds

• Updated with changes from 2026-04-17
• Auto-generated by create-pull-request
• Update .onnxrt-commit to e3063083e1ec1621ecb6c41afa30104c7e4a8395

[causten]

Test	Batch	New Rate (f0ac4a)	Old Rate (0681c6)	Diff	Status
torchvision-resnet50	64	3,138.75	3,166.53	-0.88%	✅
torchvision-resnet50_fp16	64	6,522.98	6,820.89	-4.37%	✅
torchvision-densenet121	32	2,633.66	2,422.10	8.73%	🔆
torchvision-densenet121_fp16	32	4,392.53	4,086.15	7.50%	🔆
torchvision-inceptionv3	32	1,806.15	1,658.01	8.93%	🔆
torchvision-inceptionv3_fp16	32	2,794.20	2,677.22	4.37%	✅
cadene-inceptionv4	16	828.59	789.08	5.01%	🔆
cadene-resnext64x4	16	783.20	790.86	-0.97%	✅
slim-mobilenet	64	8,381.92	8,521.12	-1.63%	✅
slim-nasnetalarge	64	229.50	218.37	5.10%	🔆
slim-resnet50v2	64	3,291.01	3,288.39	0.08%	✅
bert-mrpc-onnx	8	1,128.89	1,108.72	1.82%	✅
bert-mrpc-tf	1	454.71	456.31	-0.35%	✅
pytorch-examples-wlang-gru	1	472.93	338.72	39.62%	🔆
pytorch-examples-wlang-lstm	1	455.42	452.66	0.61%	✅
torchvision-resnet50_1	1	740.83	748.69	-1.05%	✅
cadene-dpn92_1	1	425.00	403.71	5.27%	🔆
cadene-resnext101_1	1	368.06	323.10	13.92%	🔆
onnx-taau-downsample	1	399.93	391.86	2.06%	✅
dlrm-criteoterabyte	1	33.05	31.56	4.71%	✅
dlrm-criteoterabyte_fp16	1	52.09	50.03	4.14%	✅
agentmodel	1	12,571.74	10,347.89	21.49%	🔆
unet_fp16	2	56.44	55.66	1.39%	✅
resnet50v1_fp16	1	946.90	994.78	-4.81%	✅
resnet50v1_int8	1	932.68	943.47	-1.14%	✅
bert_base_cased_fp16	64	1,115.89	1,086.36	2.72%	✅
bert_large_uncased_fp16	32	348.00	338.39	2.84%	✅
bert_large_fp16	1	200.75	198.67	1.05%	✅
distilgpt2_fp16	16	2,116.28	2,066.44	2.41%	✅
yolov5s	1	555.43	549.43	1.09%	✅
tinyllama	1	45.65	43.80	4.23%	✅
vicuna-fastchat	1	43.98	42.63	3.17%	✅
whisper-tiny-encoder	1	414.77	406.13	2.13%	✅
whisper-tiny-decoder	1	409.69	395.21	3.67%	✅
llama2_7b	1	20.29	19.10	6.26%	🔆
qwen1.5-7b	1	23.62	23.42	0.87%	✅
phi3-3.8b	1	26.80	26.63	0.65%	✅
llama3-8b	1	21.83	21.68	0.73%	✅
whisper-large-encoder	1	10.26	10.12	1.37%	✅
whisper-large-decoder	1	99.50	101.03	-1.51%	✅
mistral-7b	1	23.83	23.64	0.80%	✅
FLUX.1-schnell	1	750.44	737.25	1.79%	✅

Check flagged results 🔆

[causten]

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 360, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 296, in main import tensorflow as tf File "/usr/local/lib/python3.10/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/python3.10/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 37, in self_check.preload_check() File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/platform/self_check.py", line 63, in preload_check from tensorflow.python.platform import _pywrap_cpu_feature_guard ImportError: librocm_smi64.so.1: cannot open shared object file: No such file or directory
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	❌	ERROR - check error output traceback Traceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 360, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 211, in main model = migraphx.parse_onnx(model_name, default_dim_value=batch) RuntimeError: /src/AMDMIGraphX/src/include/migraphx/op/convolution.hpp:103: normalize_compute_shape: CONVOLUTION: mismatched channel numbers
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance