inference

inference copied to clipboard

SDXL model download link broken

5

https://cloud.mlcommons.org/index.php/s/LCdW5RM6wgGWbxC https://cloud.mlcommons.org/index.php/s/DjnCSGyNBkWA4Ro Pages Not Found error for SDXL model links.

nvyihengz

Proposal: run clang-format and autopep8 on the existing code base; potentially add pre-commit hook for code style checking

3

The current C++ code base follows C and fortran coding style, which is a bit stale given that C++14 is used. We would like to clang-format all the C++ code...

nvzhihanj

Proposal: Change all module/folder name from hyphen to underscore

2

Python module disallows usage of hyphen ('-') in module name, and it makes importing and module run very complicated. We should change the naming of folder and module (e.g. llama2-70b)...

nvzhihanj

issue downloading dlrm-pytorch model

1

hi, I'm so sorry to bother you~ but who can tell me the way to download dlrm-pytorch model by command line?

tangds1234

【bert】result exact_match and f1 abnormal

3

In bert Offline accuracy test，I submit multi batch size. when exec response on lg.QuerySamplesComplete one by one, can get right result. ```python def issue_queries(self, query_samples): batch_size = self.batch_size if len(query_samples)...

kaiwuhuang

CNNDM download script fails if we use python 3.10 but works fine for python3.9. The exact error is added below. ``` $ cm run script --tags=get,dataset,cnndm,_calibration -j * cm run...

arjunsuresh

why onnx.load("resnet50_v1.pth") when I use pytorch backend?

11

is not onnx.load() with args "xxx.onnx"? vision/classification_and_detection/python/backend_pytorch.py line 34:self.model = onnx.load(model_path) when I run "./run_local.sh pytorch resnet50 cpu" the backend_pytorch.py is called,but model_path is "resnet50_v1.pth" and it caused bug onnx...

qq1243196045

use MLPerf inference benchmark testing on NPU

1

May I ask if I can use MLPerf inference benchmark testing on NPU? What do I need to do? Is there any relevant documentation available？

datutu-L

Questions about Llama benchmarks

2

Really exciting to see progress on LLM benchmarking in the `loadgen` codebase. I do wonder that: a) Is `First Token latency` going to be the only metric? Sometimes we might...

ljk3210

Bump scipy from 1.9.1 to 1.10.0 in /text_to_image

2

Bumps [scipy](https://github.com/scipy/scipy) from 1.9.1 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]