[ET-VK] Add missing VMA flush/invalidate calls in StagingBuffer copy methods

[SS-JIA]

Stack from ghstack (oldest at bottom):

• -> [ET-VK] Add missing VMA flush/invalidate calls in StagingBuffer copy methods #17341

copy_from correctly calls vmaFlushAllocation after writing to the staging buffer, and copy_to correctly calls vmaInvalidateAllocation before reading, but the cast-and-copy variants were missing these calls. On devices with non-coherent memory, this could cause the GPU to read stale data (missing flush) or the CPU to read stale data (missing invalidate). This change adds the missing vmaFlushAllocation to cast_and_copy_from and cast_half_to_float_and_copy_from, and the missing vmaInvalidateAllocation to cast_and_copy_to. cast_float_to_half_and_copy_to already had the invalidate call and was not changed.

Authored with Claude.

Differential Revision: D92843801

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17341

• 📄 Preview Python docs built from this PR

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

❌ 8 New Failures, 1 Pending, 3 Unrelated Failures

As of commit 1c96f11 with merge base ba89c69 ():

NEW FAILURES - The following jobs have failed:

• pull / test-moshi-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 6516095ea06a0e97195b62d6a93a16840874628a9055bb0ba478a824250d3acf /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (mistralai, Voxtral-Mini-3B-2507, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 09a6640d30be03775414da509ef09844586da0be6fff69577b1387ee0a1a44cf /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-large-v3-turbo, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t 1dc0897480aa6241d8ac58ed0ee85edc27f24f434c9f29ba1d27784b32478ba2 /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 3cfdb7cb52b7498e2fd99275330f4a44c447bbe88bbae19f4fd6e4e65bbfa535 /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-large-v3-turbo, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t cd351d3c61257684344636d6fc0054580f2e0b6a1c3be24769dd7bd1503fde06 /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-small, non-quantized) / linux-job (gh)
  RuntimeError: Command docker exec -t cfe36da8c12266ef91a7a515355160b3038eba487e2b89ad47282b46b803e406 /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-small, quantized-int4-tile-packed) / linux-job (gh)
  RuntimeError: Command docker exec -t 3c923c81854335307c0fe5502b7183678d26dd1bd881eb7100029a9429962bcb /exec failed with exit code 1
• Test CUDA Builds / test-model-cuda-e2e (openai, whisper-small, quantized-int4-weight-only) / linux-job (gh)
  RuntimeError: Command docker exec -t ab88ff3e4e57100e2a618cf20ebf517ccbb7e7a58d5d47316f4b12151173b7dd /exec failed with exit code 1

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

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

• pull / test-samsung-quantmodels-linux / linux-job (gh) (trunk failure)
  ##[error]The operation was canceled.
• Test Metal Backend / test-model-metal-e2e (openai, whisper-large-v3-turbo, non-quantized) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test Metal Backend / test-model-metal-e2e (openai, whisper-small, non-quantized) / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.