Skip to content

Commit

Permalink
Auto-merge updates from auto-update branch
Browse files Browse the repository at this point in the history
  • Loading branch information
@mlcommons-bot
mlcommons-bot committed Jan 1, 2025
2 parents 149bc16 + f1ab5ed commit 8ecf78e
Show file tree
Hide file tree
Showing 51 changed files with 1,151 additions and 1,161 deletions.
16 changes: 8 additions & 8 deletions closed/MLCommons/systems/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config.json
View file
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
{
"accelerator_frequency": "2610000 MHz",
"accelerator_frequency": "2520000 MHz",
"accelerator_host_interconnect": "N/A",
"accelerator_interconnect": "N/A",
"accelerator_interconnect_topology": "",
"accelerator_memory_capacity": "23.54595947265625 GB",
"accelerator_memory_capacity": "23.64971923828125 GB",
"accelerator_memory_configuration": "N/A",
"accelerator_model_name": "NVIDIA GeForce RTX 4090",
"accelerator_on-chip_memories": "",
Expand All @@ -16,17 +16,17 @@
"host_network_card_count": "1",
"host_networking": "Gig Ethernet",
"host_networking_topology": "N/A",
"host_processor_caches": "L1d cache: 512 KiB, L1i cache: 512 KiB, L2 cache: 16 MiB, L3 cache: 64 MiB",
"host_processor_core_count": "16",
"host_processor_frequency": "5881.0000",
"host_processor_caches": "L1d cache: 576 KiB, L1i cache: 384 KiB, L2 cache: 24 MiB, L3 cache: ",
"host_processor_core_count": "24",
"host_processor_frequency": "5800.0000",
"host_processor_interconnect": "",
"host_processor_model_name": "AMD Ryzen 9 7950X 16-Core Processor",
"host_processor_model_name": "13th Gen Intel(R) Core(TM) i9-13900K",
"host_processors_per_node": "1",
"host_storage_capacity": "6.8T",
"host_storage_capacity": "9.4T",
"host_storage_type": "SSD",
"hw_notes": "",
"number_of_nodes": "1",
"operating_system": "Ubuntu 20.04 (linux-6.8.0-51-generic-glibc2.31)",
"operating_system": "Ubuntu 20.04 (linux-6.8.0-49-generic-glibc2.31)",
"other_software_stack": "Python: 3.8.10, GCC-9.4.0, Using Docker , CUDA 12.2",
"status": "available",
"submitter": "MLCommons",
Expand Down
18 changes: 6 additions & 12 deletions ...inal-gpu-tensorrt-vdefault-default_config/stable-diffusion-xl/offline/README.md
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,3 @@
This experiment is generated using the [MLCommons Collective Mind automation framework (CM)](https://github.com/mlcommons/cm4mlops).

*Check [CM MLPerf docs](https://docs.mlcommons.org/inference) for more details.*

## Host platform
Expand All @@ -19,7 +17,7 @@ pip install -U cmind

cm rm cache -f

cm pull repo mlcommons@mlperf-automations --checkout=ca9263aff2a56ee495a03382fb678506581d9da9
cm pull repo mlcommons@mlperf-automations --checkout=48ea6b46a7606d1c5d74909e94d5599dbe7ff9e1

cm run script \
--tags=app,mlperf,inference,generic,_nvidia,_sdxl,_tensorrt,_cuda,_valid,_r4.1-dev_default,_offline \
Expand All @@ -41,8 +39,8 @@ cm run script \
--env.CM_RUN_MLPERF_SUBMISSION_PREPROCESSOR=yes \
--env.CM_MLPERF_INFERENCE_PULL_CODE_CHANGES=yes \
--env.CM_MLPERF_INFERENCE_PULL_SRC_CHANGES=yes \
--env.OUTPUT_BASE_DIR=/home/arjun/gh_action_results \
--env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/home/arjun/gh_action_submissions \
--env.OUTPUT_BASE_DIR=/cm-mount/home/arjun/gh_action_results \
--env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/cm-mount/home/arjun/gh_action_submissions \
--env.CM_MLPERF_SUBMITTER=MLCommons \
--env.CM_USE_DATASET_FROM_HOST=yes \
--env.CM_USE_MODEL_FROM_HOST=yes \
Expand Down Expand Up @@ -71,7 +69,7 @@ cm run script \
--env.CM_DOCKER_REUSE_EXISTING_CONTAINER=yes \
--env.CM_DOCKER_DETACHED_MODE=yes \
--env.CM_MLPERF_INFERENCE_RESULTS_DIR_=/home/arjun/gh_action_results/valid_results \
--env.CM_DOCKER_CONTAINER_ID=c30d1a720abb \
--env.CM_DOCKER_CONTAINER_ID=2578b35d628e \
--env.CM_MLPERF_LOADGEN_COMPLIANCE_TEST=TEST04 \
--add_deps_recursive.compiler.tags=gcc \
--add_deps_recursive.coco2014-original.tags=_full \
Expand Down Expand Up @@ -104,11 +102,7 @@ cm run script \
--v=False \
--print_env=False \
--print_deps=False \
--dump_version_info=True \
--env.OUTPUT_BASE_DIR=/cm-mount/home/arjun/gh_action_results \
--env.CM_MLPERF_INFERENCE_SUBMISSION_DIR=/cm-mount/home/arjun/gh_action_submissions \
--env.SDXL_CHECKPOINT_PATH=/home/cmuser/CM/repos/local/cache/d0f05efed7544e3a/stable_diffusion_fp16 \
--env.MLPERF_SCRATCH_PATH=/home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a
--dump_version_info=True
```
*Note that if you want to use the [latest automation recipes](https://docs.mlcommons.org/inference) for MLPerf (CM scripts),
you should simply reload mlcommons@mlperf-automations without checkout and clean CM cache as follows:*
Expand All @@ -129,4 +123,4 @@ Model Precision: int8
### Accuracy Results

### Performance Results
`Samples per second`: `0.698`
`Samples per second`: `0.697739`
44 changes: 22 additions & 22 deletions ...nal-gpu-tensorrt-vdefault-default_config/stable-diffusion-xl/offline/accuracy_console.out
View file
Original file line number Diff line number Diff line change
@@ -1,30 +1,30 @@
[2024-12-29 07:34:13,589 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
[2025-01-01 07:35:05,442 main.py:229 INFO] Detected system ID: KnownSystem.RTX4090x1
/home/cmuser/.local/lib/python3.8/site-packages/torchvision/datapoints/__init__.py:12: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
/home/cmuser/.local/lib/python3.8/site-packages/torchvision/transforms/v2/__init__.py:54: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
[2024-12-29 07:34:14,715 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/stable-diffusion-xl/Offline
[2024-12-29 07:34:14,715 __init__.py:46 INFO] Running command: python3 -m code.stable-diffusion-xl.tensorrt.harness --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/stable-diffusion-xl/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=5000 --test_mode="AccuracyOnly" --gpu_batch_size=2 --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf" --tensor_path="build/preprocessed_data/coco2014-tokenized-sdxl/5k_dataset_final/" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/0f2b4a4ab1aa48d092f808fe52515e2a.conf" --gpu_inference_streams=1 --gpu_copy_streams=1 --gpu_engines="./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIP-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIPWithProj-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-UNetXL-Offline-gpu-b2-int8.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-VAE-Offline-gpu-b2-fp32.custom_k_99_MaxP.plan" --scenario Offline --model stable-diffusion-xl
[2024-12-29 07:34:14,715 __init__.py:53 INFO] Overriding Environment
[2025-01-01 07:35:06,464 generate_conf_files.py:107 INFO] Generated measurements/ entries for RTX4090x1_TRT/stable-diffusion-xl/Offline
[2025-01-01 07:35:06,464 __init__.py:46 INFO] Running command: python3 -m code.stable-diffusion-xl.tensorrt.harness --logfile_outdir="/cm-mount/home/arjun/gh_action_results/valid_results/RTX4090x1-nvidia_original-gpu-tensorrt-vdefault-default_config/stable-diffusion-xl/offline/accuracy" --logfile_prefix="mlperf_log_" --performance_sample_count=5000 --test_mode="AccuracyOnly" --gpu_batch_size=2 --mlperf_conf_path="/home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf" --tensor_path="build/preprocessed_data/coco2014-tokenized-sdxl/5k_dataset_final/" --use_graphs=true --user_conf_path="/home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/8255eff47682486f875ae6f8c8cd3191.conf" --gpu_inference_streams=1 --gpu_copy_streams=1 --gpu_engines="./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIP-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIPWithProj-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-UNetXL-Offline-gpu-b2-int8.custom_k_99_MaxP.plan,./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-VAE-Offline-gpu-b2-fp32.custom_k_99_MaxP.plan" --scenario Offline --model stable-diffusion-xl
[2025-01-01 07:35:06,464 __init__.py:53 INFO] Overriding Environment
/home/cmuser/.local/lib/python3.8/site-packages/torchvision/datapoints/__init__.py:12: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
/home/cmuser/.local/lib/python3.8/site-packages/torchvision/transforms/v2/__init__.py:54: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
warnings.warn(_BETA_TRANSFORMS_WARNING)
[2024-12-29 07:34:16,327 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIP-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan.
[2024-12-29 07:34:16,428 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIPWithProj-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan.
[2024-12-29 07:34:16,936 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-UNetXL-Offline-gpu-b2-int8.custom_k_99_MaxP.plan.
[2024-12-29 07:34:17,974 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-VAE-Offline-gpu-b2-fp32.custom_k_99_MaxP.plan.
[2024-12-29 07:34:18,939 backend.py:96 INFO] Enabling cuda graphs for unet
[2024-12-29 07:34:19,149 backend.py:154 INFO] captured graph for BS=1
[2024-12-29 07:34:19,402 backend.py:154 INFO] captured graph for BS=2
[2024-12-29 07:34:19,402 harness.py:207 INFO] Start Warm Up!
[2024-12-29 07:34:25,225 harness.py:209 INFO] Warm Up Done!
[2024-12-29 07:34:25,225 harness.py:211 INFO] Start Test!
[2024-12-29 09:33:49,131 backend.py:801 INFO] [Server] Received 5000 total samples
[2024-12-29 09:33:49,132 backend.py:809 INFO] [Device 0] Reported 5000 samples
[2024-12-29 09:33:49,132 harness.py:214 INFO] Test Done!
[2024-12-29 09:33:49,132 harness.py:216 INFO] Destroying SUT...
[2024-12-29 09:33:49,132 harness.py:219 INFO] Destroying QSL...
[2025-01-01 07:35:07,887 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIP-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan.
[2025-01-01 07:35:07,986 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIPWithProj-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan.
[2025-01-01 07:35:08,499 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-UNetXL-Offline-gpu-b2-int8.custom_k_99_MaxP.plan.
[2025-01-01 07:35:09,539 backend.py:71 INFO] Loading TensorRT engine: ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-VAE-Offline-gpu-b2-fp32.custom_k_99_MaxP.plan.
[2025-01-01 07:35:10,501 backend.py:96 INFO] Enabling cuda graphs for unet
[2025-01-01 07:35:10,710 backend.py:154 INFO] captured graph for BS=1
[2025-01-01 07:35:10,963 backend.py:154 INFO] captured graph for BS=2
[2025-01-01 07:35:10,963 harness.py:207 INFO] Start Warm Up!
[2025-01-01 07:35:16,788 harness.py:209 INFO] Warm Up Done!
[2025-01-01 07:35:16,788 harness.py:211 INFO] Start Test!
[2025-01-01 09:34:41,246 backend.py:801 INFO] [Server] Received 5000 total samples
[2025-01-01 09:34:41,247 backend.py:809 INFO] [Device 0] Reported 5000 samples
[2025-01-01 09:34:41,247 harness.py:214 INFO] Test Done!
[2025-01-01 09:34:41,247 harness.py:216 INFO] Destroying SUT...
[2025-01-01 09:34:41,247 harness.py:219 INFO] Destroying QSL...
benchmark : Benchmark.SDXL
buffer_manager_thread_count : 0
data_dir : /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/data
Expand All @@ -33,7 +33,7 @@ gpu_copy_streams : 1
gpu_inference_streams : 1
input_dtype : int32
input_format : linear
log_dir : /home/cmuser/CM/repos/local/cache/dfbf240f980947f5/repo/closed/NVIDIA/build/logs/2024.12.29-07.34.12
log_dir : /home/cmuser/CM/repos/local/cache/dfbf240f980947f5/repo/closed/NVIDIA/build/logs/2025.01.01-07.35.04
mlperf_conf_path : /home/cmuser/CM/repos/local/cache/c1d8c371d52d46a3/inference/mlperf.conf
model_path : /home/cmuser/CM/repos/local/cache/5b2b0cc913a4453a/models/SDXL/
offline_expected_qps : 0.0
Expand All @@ -44,7 +44,7 @@ system : SystemConfiguration(host_cpu_conf=CPUConfiguration(layout={CPU(name='13
tensor_path : build/preprocessed_data/coco2014-tokenized-sdxl/5k_dataset_final/
test_mode : AccuracyOnly
use_graphs : True
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/0f2b4a4ab1aa48d092f808fe52515e2a.conf
user_conf_path : /home/cmuser/CM/repos/mlcommons@mlperf-automations/script/generate-mlperf-inference-user-conf/tmp/8255eff47682486f875ae6f8c8cd3191.conf
system_id : RTX4090x1
config_name : RTX4090x1_stable-diffusion-xl_Offline
workload_setting : WorkloadSetting(HarnessType.Custom, AccuracyTarget.k_99, PowerSetting.MaxP)
Expand All @@ -60,7 +60,7 @@ cpu_freq : None
[I] Loading bytes from ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-CLIPWithProj-Offline-gpu-b2-fp16.custom_k_99_MaxP.plan
[I] Loading bytes from ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-UNetXL-Offline-gpu-b2-int8.custom_k_99_MaxP.plan
[I] Loading bytes from ./build/engines/RTX4090x1/stable-diffusion-xl/Offline/stable-diffusion-xl-VAE-Offline-gpu-b2-fp32.custom_k_99_MaxP.plan
[2024-12-29 09:33:49,425 run_harness.py:166 INFO] Result: Accuracy run detected.
[2025-01-01 09:34:41,537 run_harness.py:166 INFO] Result: Accuracy run detected.

======================== Result summaries: ========================

Loading

0 comments on commit 8ecf78e

Please sign in to comment.