OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

Added torchao nightly workflow (#128152)

Browse Source 
Summary:
Add torchao benchmark workflow, upload the artifacts to GHA.

X-link: https://github.com/pytorch/benchmark/pull/2273

Test Plan:
```
python run_benchmark.py torchao --ci
```

Differential Revision: D58140479

Pulled By: xuzhao9

Pull Request resolved: https://github.com/pytorch/pytorch/pull/128152
Approved by: https://github.com/jerryzh168
This commit is contained in:
Xu Zhao 2024-06-07 17:52:13 +00:00 committed by PyTorch MergeBot
parent 0c7f4353e5
commit 82d7a36a27
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
benchmarks/dynamo/common.py
View File

@ -3975,9 +3975,12 @@ def run(runner, args, original_dir=None):
assert "cuda" in args.devices, "Quantization requires CUDA device." assert "cuda" in args.devices, "Quantization requires CUDA device."
assert args.bfloat16, "Quantization requires dtype bfloat16." assert args.bfloat16, "Quantization requires dtype bfloat16."
try: try:
from .torchao_backend import setup_baseline, torchao_optimize_ctx
except ImportError:
from torchao_backend import setup_baseline, torchao_optimize_ctx from torchao_backend import setup_baseline, torchao_optimize_ctx
except ImportError:
from userbenchmark.dynamo.dynamobench.torchao_backend import (
setup_baseline,
torchao_optimize_ctx,
)
setup_baseline() setup_baseline()
baseline_ctx = functools.partial( baseline_ctx = functools.partial(