Fix safe_int_mm for H100

[jainapurva]

No description provided.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/882

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit c7e5fdf with merge base 85d03de ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[HDCharles]

can you make sure the model runs on the specified device given these changes? it looksl ike they don't. I think you need to go back and if this is an issue with .to(device) after compile, can you change it so it does compile right at the end and does .to(device) right beforehand?

[jerryzh168]

can you make sure the model runs on the specified device given these changes? it looksl ike they don't. I think you need to go back and if this is an issue with .to(device) after compile, can you change it so it does compile right at the end and does .to(device) right beforehand?

@HDCharles should we refactor the quantization code in eval/benchmark/hf_eval to a util? lots of duplications right now I think