use helion instead of triton for low precision attention quantization kernels

[howardzhang-cv]

Stack from ghstack (oldest at bottom):

• -> use helion instead of triton for low precision attention quantization kernels #3880
• Added benchmarking for new torchao low precision attention api #3865
• Added new API for low precision fp8 attention using FA3 #3857

Summary:

Test Plan: python benchmarks/prototype/attention/eval_flux_model.py --compile --num_prompts 1

Reviewers:

Subscribers:

Tasks:

Tags:

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3880

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 21782a0 with merge base d4c1ba3 ():

NEW FAILURE - The following job has failed:

• PR Label Check / Check PR Labels (gh)
  Process completed with exit code 1.

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

[howardzhang-cv]

@yf225 Here is the compiler error. I didn't do the MRE since I was afraid some context would be lost since I'm not sure exactly what part leads to the error. helion_compiler_error.txt

[howardzhang-cv]

Merged this with #3857