Pass in a JSON file to driver

[kahmed10]

Motivation

use a JSON file to configure the migraphx driver.

Technical Details

Example JSON:

{
  "gpu": true,
  "fp16": true,
  "exhaustive-tune": true,
  "iterations": 5,
  "input-dim": ["@input_tensor:0", 1, 3, 224, 224]
}

Changelog Category

Add a CHANGELOG.md entry for any option other than Not Applicable

• • Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

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

Test	Batch	New Rate (31c74a)	Old Rate (241f7a)*	Diff	Status
torchvision-resnet50	64	3,156.85	3,158.05	-0.04%	✅
torchvision-resnet50_fp16	64	6,587.74	6,678.10	-1.35%	✅
torchvision-densenet121	32	2,683.35	2,705.33	-0.81%	✅
torchvision-densenet121_fp16	32	4,535.46	4,480.31	1.23%	✅
torchvision-inceptionv3	32	773.00	1,772.37	-56.39%	🔴
torchvision-inceptionv3_fp16	32	2,797.69	2,613.31	7.06%	🔆
cadene-inceptionv4	16	825.48	444.89	85.55%	🔆
cadene-resnext64x4	16	345.27	412.50	-16.30%	🔴
slim-mobilenet	64	7,679.70	8,419.17	-8.78%	🔴
slim-nasnetalarge	64	nan	nan	nan	❌
slim-resnet50v2	64	3,284.90	1,641.82	100.08%	🔆
bert-mrpc-onnx	8	1,172.01	1,165.20	0.58%	✅
bert-mrpc-tf	1	487.64	492.10	-0.91%	✅
pytorch-examples-wlang-gru	1	379.86	334.96	13.41%	🔆
pytorch-examples-wlang-lstm	1	450.74	469.54	-4.00%	✅
torchvision-resnet50_1	1	746.05	760.64	-1.92%	✅
cadene-dpn92_1	1	447.59	457.65	-2.20%	✅
cadene-resnext101_1	1	362.75	363.68	-0.26%	✅
onnx-taau-downsample	1	400.62	401.93	-0.32%	✅
dlrm-criteoterabyte	1	32.47	12.36	162.69%	🔆
dlrm-criteoterabyte_fp16	1	51.80	29.66	74.67%	🔆
agentmodel	1	10,025.37	10,523.13	-4.73%	✅
unet_fp16	2	56.74	57.23	-0.85%	✅
resnet50v1_fp16	1	957.96	959.87	-0.20%	✅
resnet50v1_int8	1	218.22	942.92	-76.86%	🔴
bert_base_cased_fp16	64	976.03	1,092.47	-10.66%	🔴
bert_large_uncased_fp16	32	346.02	345.19	0.24%	✅
bert_large_fp16	1	207.64	203.23	2.17%	✅
distilgpt2_fp16	16	2,097.51	2,096.77	0.04%	✅
yolov5s	1	567.85	564.74	0.55%	✅
tinyllama	1	45.96	46.00	-0.08%	✅
vicuna-fastchat	1	44.12	44.04	0.18%	✅
whisper-tiny-encoder	1	420.39	419.55	0.20%	✅
whisper-tiny-decoder	1	416.76	414.85	0.46%	✅
llama2_7b	1	20.55	20.42	0.63%	✅
qwen1.5-7b	1	9.80	21.75	-54.93%	🔴
phi3-3.8b	1	26.85	26.81	0.17%	✅
llama3-8b	1	21.78	21.83	-0.26%	✅
whisper-large-encoder	1	10.16	6.50	56.44%	🔆
whisper-large-decoder	1	106.18	106.80	-0.58%	✅
mistral-7b	1	21.64	23.85	-9.27%	🔴
FLUX.1-schnell	1	113.61	763.88	-85.13%	🔴

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/python3.10/dist-packages/tensorflow/init.py", line 38, in from tensorflow.python.tools import module_util as _module_util File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/init.py", line 36, in from tensorflow.python import pywrap_tensorflow as _pywrap_tensorflow File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/pywrap_tensorflow.py", line 26, 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: libamdhip64.so.6: 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 2026-06-17 19:13:34.117996 [WARN] [/data/src/onnx/onnx_parser.cpp:282] Model has unbound symbolic dimension(s): batch_size, encoder_sequence_length, feature_size. These default to 1 and may cause unexpected behavior. Try setting --dim-param @<name> <value> or --input-dim @<input> <dims> if program compilation fails. 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 224, in main model = migraphx.parse_onnx(model_name, default_dim_value=batch) RuntimeError: /data/src/include/migraphx/op/convolution.hpp:113: normalize_compute_shape: CONVOLUTION: mismatched channel numbers: input channels (1) != weights channels (80) * group (1)
whisper-large-decoder	✅	PASSED: MIGraphX meets tolerance
mistral-7b	✅	PASSED: MIGraphX meets tolerance
FLUX.1-schnell	✅	PASSED: MIGraphX meets tolerance