Use symmetric weights for convs and int8 in the default quantizer

[mcremon-meta]

Summary:
As titled. int8 should give better performance with Cadence kernels, since they're not improving uint8 anymore.
The upcoming (quantized) convolution kernel needs symmetric weights, so we make that change as well.

Differential Revision: D69405797

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8344

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 5 Unrelated Failures

As of commit 4b02da3 with merge base ee7d388 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for backends/cadence/aot/export_example.py:
• pull / test-binary-size-linux / linux-job (gh)
  /pytorch/executorch/kernels/portable/cpu/util/advanced_index_util.cpp:58:18: error: unused variable 'input_shape' [-Werror,-Wunused-variable]

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / test-llama-runner-qnn-linux (fp32, qnn_16a16w, qnn) / linux-job (gh) (similar failure)
  undefined reference to executorch::runtime::tensor_shape_to_c_string(executorch::runtime::Span)'`

BROKEN TRUNK - The following jobs failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / test-binary-size-linux-gcc / linux-job (gh) (trunk failure)
  /pytorch/executorch/kernels/portable/cpu/util/advanced_index_util.cpp:58:18: error: variable 'input_shape' set but not used [-Werror=unused-but-set-variable]
• pull / test-llama-runner-qnn-linux (fp32, qnn_8a8w, qnn) / linux-job (gh) (trunk failure)
  undefined reference to executorch::runtime::tensor_shape_to_c_string(executorch::runtime::Span)'`
• pull / test-selective-build-linux / linux-job (gh) (trunk failure)
  undefined reference to executorch::runtime::tensor_shape_to_c_string(executorch::runtime::Span)'`
• pull / test-static-llama-qnn-linux / linux-job (gh) (trunk failure)
  undefined reference to executorch::runtime::tensor_shape_to_c_string(executorch::runtime::Span)'`

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

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D69405797

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D69405797

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D69405797