inference
inference copied to clipboard
mlcommons
Reference implementations of MLPerf™ inference benchmarks
When I want to run the 3dunet workload, it ends up with a segmentation fault which is quite not clear what is the exact problem. See the output below: ```...
When I run the text_to_image command ``` python3 main.py --dataset "coco-1024" --dataset-path coco2014 \ --profile stable-diffusion-xl-pytorch --model-path ./model/stable_diffusion_fp32 \ --dtype fp32 --device cuda --scenario Offline ``` I see a bunch...
We propose to add some basic unit test framework (likely pytest) and tests to the inference repo. Ideally, it should test: - All configuration (mlperf.conf, user.conf) is valid and working...
Hello everyone. I recently moved space on my system and removed files that weighed especially much. Now when I launch "3-d Unet" I get an error. Is there any way...
The submission generation rules for inference says that the `accuracy.txt` file should be generated from the accuracy scripts. My interpretation of this is that one should run the reference accuracy...
For Llama-2 inference, I set the total sample count to 1024 to see how much time is needed and what is the final output. I see multiple sample runs: ```...
Trying to run offline retinanet in a container with one Nvidia GPU: cm run script --tags=run-mlperf,inference,_find-performance,_full,_r4.1-dev --model=retinanet --implementation=nvidia --framework=tensorrt --category=datacenter --scenario=Offline --execution_mode=test --device=cuda --gpu_name=l4 --docker_cache=no --quiet --test_query_count=500 Fails execution of...
Hello everyone. I have been using MLperf benchmarks for some time. And I have a small list of questions about them. I am asking them here because I have not...
In the inference/vision/classification_and_detection/setup.py there is no package with the name **mlperf_loadgen**? Instead it is **mlcommons_loadgen.**
