Polish UI (#5319)
Summary:
Enable all iOS 18 features by a single `--coreml-ios 18` argument, rather than one arg for each individual feature
Export our current best model by
```
python -m examples.models.llama2.export_llama \
-c <download-path>/consolidated.00.pth \
-p <download-path>/params.json \
--disable_dynamic_shape -kv \
--coreml \
--coreml-ios 18 \
--coreml-quantize b4w
```
i.e.
* FP16 activation
* Static sequence length
* In-place KV cache
* Fused scaled dot product attention
* 4-bit per-block weight
Pull Request resolved: https://github.com/pytorch/executorch/pull/5319
Reviewed By: kirklandsign
Differential Revision: D62616303
Pulled By: cccclai
fbshipit-source-id: 416a8acec785662ad76d04ea0b949ce3393308fe Y
yifan_shen3 committed
c080c486de451f8965dbc64f9dd9f2b36f0a64b6
Parent: 9301ebb
Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
on 9/13/2024, 1:55:05 PM