share embeddding and output

[cccclai]

Differential Revision: D64189995

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6800

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures

As of commit 08cb3f7 with merge base 4b7a60f ():

NEW FAILURES - The following jobs have failed:

• pull / test-llama-runner-linux (fp32, xnnpack+custom) / linux-job (gh)
  RuntimeError: a and b must have same reduction dim, but got [1, 768] X [32000, 768].
• pull / test-llama-runner-linux (fp32, xnnpack+custom+qe) / linux-job (gh)
  RuntimeError: a and b must have same reduction dim, but got [1, 768] X [32000, 768].
• pull / test-llava-runner-linux / linux-job (gh)
  test_prefill_logits

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: D64189995

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D64189995

[cccclai]

@chiwwang here is one thing we can do to optimize the memory. For 1b model, the embedding is shared with the last linear weight, so ideally, we can save more memory if it's enabled.

[chiwwang]

@shewu-quic for awareness. This might also help us reduce memory usage.

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.