add support for Qualcomm QCM6490

[9rum]

Summary

This PR adds support for Qualcomm QCM6490, which has been discussed in issue #7356.

Fixes

Fixes #7356.

Test plan

The changes in this PR have been tested with the official Llama example.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16331

• 📄 Preview Python docs built from this PR

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

❌ 5 New Failures, 1 Unrelated Failure

As of commit f1634d9 with merge base 0fb422f ():

NEW FAILURES - The following jobs have failed:

• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh)
  /pytorch/executorch/build-x86/schema/include/executorch/backends/qualcomm/qc_compiler_spec_generated.h:136:10: error: duplicate case value: 'QCM6490' and 'SM8350' both equal '35'
• pull / test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job (gh)
  /pytorch/executorch/build-x86/schema/include/executorch/backends/qualcomm/qc_compiler_spec_generated.h:136:10: error: duplicate case value: 'QCM6490' and 'SM8350' both equal '35'
• pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh)
  /pytorch/executorch/build-x86/schema/include/executorch/backends/qualcomm/qc_compiler_spec_generated.h:136:10: error: duplicate case value: 'QCM6490' and 'SM8350' both equal '35'
• pull / test-static-llama-qnn-linux (stories_260k_bc) / linux-job (gh)
  /pytorch/executorch/build-x86/schema/include/executorch/backends/qualcomm/qc_compiler_spec_generated.h:136:10: error: duplicate case value: 'QCM6490' and 'SM8350' both equal '35'
• pull / unittest-arm-backend-with-no-fvp (test_pytest_models) / linux-job (gh)
  RuntimeError: Command docker exec -t ff410032fbbcbbd8cb86819a8aea6eab460d02e40675b0bf768ba3c30ad4e267 /exec failed with exit code 1

UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:

• pull / android / run-emulator (gh) (#16137)
  Timeout waiting for emulator to boot.

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

[meta-cla]

Hi @9rum!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[9rum]

@pytorchbot label "release notes: backends"

[pytorch-bot]

Didn't find following labels among repository labels: release notes: backends

[9rum]

@pytorchbot label "release notes: qualcomm"

[nil-is-all]

Hi @shewu-quic @chenweng-quic @winskuo-quic @DannyYuyang-quic @haowhsu-quic if you take a look at this PR fixing #7356

[cccclai]

Thank you for contributing! I wonder how you run llama on QCM6490? It seems like v68 and doesn't support block wise quantization, which means the accuracy won't be ideal

[9rum]

@cccclai Thank you for your kind reply.
We first quantize Llama 3.2 1B using SmoothQuant then run in 16a8w.
In such settings, the MMLU accuracy was 51.16%.

BTW, I see there is an enum value conflict: error: duplicate case value: 'QCM6490' and 'SM8350' both equal '35'.
This error was not found in the previous release where SM8350 was not supported.
However, simply setting SoC number to SM8350 does not cover QCM6490 since their VTCM sizes are different.
Should I remove QCM6490 and comment it out?