Auto-merge updates from auto-update branch

Author: mlcommons-bot

open/MLCommons/measurements/default-mlcommons_cpp-cpu-onnxruntime-default_config/README.md

@@ -1,3 +1,3 @@
 | Model     | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
 |-----------|------------|------------|--------------|-------------------|
-| retinanet | offline    |     49.593 |        0.422 | -                 |
+| retinanet | offline    |     49.593 |        0.423 | -                 |

open/MLCommons/measurements/default-mlcommons_cpp-cpu-onnxruntime-default_config/retinanet/offline/README.md

@@ -2,10 +2,9 @@
 
 ## Host platform
 
-* OS version: Linux-6.11.0-1018-azure-x86_64-with-glibc2.34
+* OS version: Linux-6.11.0-1018-azure-x86_64-with-glibc2.39
 * CPU version: x86_64
-* Python version: 3.8.18 (default, Dec 12 2024, 19:15:30) 
-[GCC 13.2.0]
+* Python version: 3.12.11 (main, Jun  4 2025, 04:14:08) [GCC 13.3.0]
 * MLC version: unknown
 
 ## MLC Run Command
@@ -17,16 +16,16 @@ pip install -U mlcflow
 
 mlc rm cache -f
 
-mlc pull repo GATEOverflow@mlperf-automations --checkout=99f4c475968737d8b3f73f1c9a476fdba6eeafce
+mlc pull repo mlcommons@mlperf-automations --checkout=7541b246c90a3ba5e8e444f015b2f04ed74c544d
 
 
 ```
 *Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf,
- you should simply reload GATEOverflow@mlperf-automations without checkout and clean MLC cache as follows:*
+ you should simply reload mlcommons@mlperf-automations without checkout and clean MLC cache as follows:*
 
 ```bash
-mlc rm repo GATEOverflow@mlperf-automations
-mlc pull repo GATEOverflow@mlperf-automations
+mlc rm repo mlcommons@mlperf-automations
+mlc pull repo mlcommons@mlperf-automations
 mlc rm cache -f
 
 ```
@@ -41,4 +40,4 @@ Model Precision: fp32
 `mAP`: `49.593`, Required accuracy for closed division `>= 37.1745`
 
 ### Performance Results 
-`Samples per second`: `0.421802`
+`Samples per second`: `0.423191`

open/MLCommons/measurements/default-mlcommons_cpp-cpu-onnxruntime-default_config/retinanet/offline/accuracy_console.out

@@ -1,6 +1,6 @@
-User Conf path: /home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/b421cc2bc3144817948999f3aff3e7d4.conf
-Dataset Preprocessed path: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3261d9f3
-Dataset List filepath: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3261d9f3/annotations/openimages-mlperf.json
+User Conf path: /home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/8adf11431c45492ba61d662114b3b330.conf
+Dataset Preprocessed path: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_e18e804e
+Dataset List filepath: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_e18e804e/annotations/openimages-mlperf.json
 Scenario: Offline
 Mode: AccuracyOnly
 Batch size: 1

open/MLCommons/measurements/default-mlcommons_cpp-cpu-onnxruntime-default_config/retinanet/offline/os_info.json

@@ -28,6 +28,6 @@
   "MLC_HOST_PYTHON_BITS": "64",
   "MLC_HOST_SYSTEM_NAME": "runnervmf4ws1",
   "+PATH": [
-    "/home/runner/MLC/repos/local/cache/install-python-src_2fb6b0e8/install/bin"
+    "/home/runner/MLC/repos/local/cache/install-python-src_d7e6a23d/install/bin"
   ]
 }

open/MLCommons/measurements/default-mlcommons_cpp-cpu-onnxruntime-default_config/retinanet/offline/performance_console.out

@@ -1,6 +1,6 @@
-User Conf path: /home/runner/MLC/repos/GATEOverflow@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/709a4d3644174156b83035351b1cb193.conf
-Dataset Preprocessed path: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3261d9f3
-Dataset List filepath: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_3261d9f3/annotations/openimages-mlperf.json
+User Conf path: /home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/d87b03b47d5644cdbed590d2f6e34fcc.conf
+Dataset Preprocessed path: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_e18e804e
+Dataset List filepath: /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-openimages_e18e804e/annotations/openimages-mlperf.json
 Scenario: Offline
 Mode: PerformanceOnly
 Batch size: 1

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-tf_v2.20.0-default_config/README.md

@@ -1,3 +1,3 @@
 | Model    | Scenario   |   Accuracy |   Throughput | Latency (in ms)   |
 |----------|------------|------------|--------------|-------------------|
-| resnet50 | offline    |         76 |       21.185 | -                 |
+| resnet50 | offline    |         76 |       20.951 | -                 |

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-tf_v2.20.0-default_config/resnet50/offline/README.md

@@ -16,7 +16,7 @@ pip install -U mlcflow
 
 mlc rm cache -f
 
-mlc pull repo mlcommons@mlperf-automations --checkout=9b5a4d3d98da73f02d54b4f1aac84c109a6a6472
+mlc pull repo mlcommons@mlperf-automations --checkout=5bf50be4373fb0090d23434194a8b19a619546b9
 
 
 ```
@@ -40,4 +40,4 @@ Model Precision: fp32
 `acc`: `76.0`, Required accuracy for closed division `>= 75.6954`
 
 ### Performance Results 
-`Samples per second`: `21.185`
+`Samples per second`: `20.9513`

open/MLCommons/measurements/gh_ubuntu-latest_x86-reference-cpu-tf_v2.20.0-default_config/resnet50/offline/accuracy_console.out

@@ -1,12 +1,12 @@
-python3 python/main.py --profile resnet50-tf --model "/home/runner/MLC/repos/local/cache/download-file_ml-model-resnet_f43c2d73/resnet50_v1.pb" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_0656bd0e --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_bb96a6e3/test_results/gh_ubuntu-latest x86-reference-cpu-tf-v2.20.0-default_config/resnet50/offline/accuracy" --scenario Offline --count 500 --threads 4 --user_conf /home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/6a157bc406984d0a8fff33a626e0a931.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_0656bd0e --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_b3583a31/val.txt
-INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_0656bd0e', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_b3583a31/val.txt', data_format=None, profile='resnet50-tf', scenario='Offline', max_batchsize=32, model='/home/runner/MLC/repos/local/cache/download-file_ml-model-resnet_f43c2d73/resnet50_v1.pb', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_bb96a6e3/test_results/gh_ubuntu-latest x86-reference-cpu-tf-v2.20.0-default_config/resnet50/offline/accuracy', inputs=['input_tensor:0'], outputs=['ArgMax:0'], backend='tensorflow', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_0656bd0e', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/6a157bc406984d0a8fff33a626e0a931.conf', audit_conf='audit.config', time=None, count=500, performance_sample_count=None, max_latency=None, samples_per_query=8)
-2025-09-14 16:19:53.687262: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.
-2025-09-14 16:19:53.731524: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
+python3 python/main.py --profile resnet50-tf --model "/home/runner/MLC/repos/local/cache/download-file_ml-model-resnet_e9cc4238/resnet50_v1.pb" --dataset-path /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6d9b3263 --output "/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_fc6af5a2/test_results/gh_ubuntu-latest x86-reference-cpu-tf-v2.20.0-default_config/resnet50/offline/accuracy" --scenario Offline --count 500 --threads 4 --user_conf /home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/8e831d2d2ff74466b63e628a765ed1e2.conf --accuracy --use_preprocessed_dataset --cache_dir /home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6d9b3263 --dataset-list /home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_01aab75a/val.txt
+INFO:main:Namespace(dataset='imagenet', dataset_path='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6d9b3263', dataset_list='/home/runner/MLC/repos/local/cache/extract-file_imagenet-aux-da_01aab75a/val.txt', data_format=None, profile='resnet50-tf', scenario='Offline', max_batchsize=32, model='/home/runner/MLC/repos/local/cache/download-file_ml-model-resnet_e9cc4238/resnet50_v1.pb', output='/home/runner/MLC/repos/local/cache/get-mlperf-inference-results-dir_fc6af5a2/test_results/gh_ubuntu-latest x86-reference-cpu-tf-v2.20.0-default_config/resnet50/offline/accuracy', inputs=['input_tensor:0'], outputs=['ArgMax:0'], backend='tensorflow', device=None, model_name='resnet50', threads=4, qps=None, cache=0, cache_dir='/home/runner/MLC/repos/local/cache/get-preprocessed-dataset-imagenet_6d9b3263', preprocessed_dir=None, use_preprocessed_dataset=True, accuracy=True, find_peak_performance=False, debug=False, user_conf='/home/runner/MLC/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/8e831d2d2ff74466b63e628a765ed1e2.conf', audit_conf='audit.config', time=None, count=500, performance_sample_count=None, max_latency=None, samples_per_query=8)
+2025-09-14 18:17:57.277675: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.
+2025-09-14 18:17:57.328598: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
 To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
-2025-09-14 16:19:54.913829: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.
+2025-09-14 18:17:58.587142: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:31] Could not find cuda drivers on your machine, GPU will not be used.
 INFO:imagenet:Loading 500 preprocessed images using 4 threads
 INFO:imagenet:loaded 500 images, cache=0, already_preprocessed=True, took=0.0sec
-WARNING:tensorflow:From /home/runner/MLC/repos/local/cache/get-git-repo_inference-src_77b77372/inference/vision/classification_and_detection/python/backend_tf.py:55: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version.
+WARNING:tensorflow:From /home/runner/MLC/repos/local/cache/get-git-repo_inference-src_e0b3e64f/inference/vision/classification_and_detection/python/backend_tf.py:55: FastGFile.__init__ (from tensorflow.python.platform.gfile) is deprecated and will be removed in a future version.
 Instructions for updating:
 Use tf.gfile.GFile.
 WARNING:tensorflow:From /opt/hostedtoolcache/Python/3.12.11/x64/lib/python3.12/site-packages/tensorflow/python/tools/strip_unused_lib.py:84: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
@@ -15,8 +15,8 @@ This API was designed for TensorFlow v1. See https://www.tensorflow.org/guide/mi
 WARNING:tensorflow:From /opt/hostedtoolcache/Python/3.12.11/x64/lib/python3.12/site-packages/tensorflow/python/tools/optimize_for_inference_lib.py:138: remove_training_nodes (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
 Instructions for updating:
 This API was designed for TensorFlow v1. See https://www.tensorflow.org/guide/migrate for instructions on how to migrate your code to TensorFlow v2.
-2025-09-14 16:20:50.402501: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)
+2025-09-14 18:18:53.021238: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)
 WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
-I0000 00:00:1757866850.487353    4015 mlir_graph_optimization_pass.cc:437] MLIR V1 optimization pass is not enabled
+I0000 00:00:1757873933.092190    4008 mlir_graph_optimization_pass.cc:437] MLIR V1 optimization pass is not enabled
 INFO:main:starting TestScenario.Offline
-TestScenario.Offline qps=0.68, mean=14.9327, time=23.661, acc=76.000%, queries=16, tiles=50.0:15.0896,80.0:23.0130,90.0:23.4861,95.0:23.5513,99.0:23.5661,99.9:23.5695
+TestScenario.Offline qps=0.67, mean=14.9658, time=23.774, acc=76.000%, queries=16, tiles=50.0:15.2893,80.0:22.5874,90.0:23.4731,95.0:23.6128,99.0:23.6713,99.9:23.6845