[slimtensor] integration into backend

[Gasoonjia]

This diff makes cuda backend actually use slimtensor.
It:
updates cuda_backends to create slimtensor from given etensor
removed duplicate etensor-driven shim layers under cuda_backend
update cmake logic in both cuda backend and aoti backend
Perf maintains the same. Shows as before.

Worth to notice that we are still keeping two sets of common shims, one is etensor-based and for metal backend, the other is slimtensor-based which used by cuda backend, to not impact metal backend work.
When Metal backend finishs the migration, we should delete the duplicate common shims and only keep slimtensor-based one.

Stack from ghstack (oldest at bottom):

• -> [slimtensor] integration into backend #16565

Differential Revision: D90606409

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16565

• 📄 Preview Python docs built from this PR

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

❌ 17 New Failures, 2 Unrelated Failures

As of commit 7d6a571 with merge base a093fe4 ():

NEW FAILURES - The following jobs have failed:

• cuda-perf / benchmark-cuda (openai/whisper-large-v3-turbo, non-quantized, openai_whisper-large-v3-turbo, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t aaee31ae535126db5566e14b40d93dd8070aad078483083f70d244b9bf8c29eb /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-tile-packed, openai_whisper-large-v... / linux-job (gh)
  RuntimeError: Command docker exec -t a9c6bb8a9c05095dd93501f1a0ed2798d7dcf38e2cba0be48408224768b60be1 /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-large-v3-turbo, quantized-int4-weight-only, openai_whisper-large-v... / linux-job (gh)
  RuntimeError: Command docker exec -t 23f3d5a0a5b9058e8ca0804f74098b0a9839029bd3b82f38b2881a7aaf7c5325 /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-medium, non-quantized, openai_whisper-medium, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t 91d91185b4016301660a3227044805f020bb7847e1cf1ee6630b15649a5f29b3 /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-medium, quantized-int4-tile-packed, openai_whisper-medium, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t 5ad53ec8fa745f1453c2b67fd1724c6d8727d27c8f8a2dd59066b09207c4bccc /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-medium, quantized-int4-weight-only, openai_whisper-medium, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t adced3124be522e582bedf6d15684b4adb08033bf15acd9d250479c30d17d363 /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-small, non-quantized, openai_whisper-small, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t 11f2c328ad3ce422e83378a0072967bfd75f3512934da5257f91fc38c842fbfd /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-small, quantized-int4-tile-packed, openai_whisper-small, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t 83d207ec1da3dcad22028eead2d0c3fafa81afca2756809b7372893b902f3714 /exec failed with exit code 1
• cuda-perf / benchmark-cuda (openai/whisper-small, quantized-int4-weight-only, openai_whisper-small, 50) / linux-job (gh)
  RuntimeError: Command docker exec -t 07c674864a847fa0e99963bf6ddfe88f80f2c1d614b9fad65f1c7b7044b22f87 /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 56352a7fe410eea399dd72ec0bcd1da3f195d02b84079eda095c610241ae7a07 /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 fb34b18f6b8a4f90a389f6008708da3da78d546dd289f4d062931394656faf74 /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 95956462471a93e245253f6c30a1ba7b9174a4df411cc970e150fcde5aaa1693 /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 b788461ef63a32390a26d59d0a5c382193ccd1c2b0578174d06630752d1aec34 /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 ffb312c13dd24442907d06924abde9e3640af173339887a7f4364586d0d73e6b /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 7d2d52fa599e4697c75c0898383d2c43fb77bbd410c91409d394044d083e2148 /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 ca85530c4d645b2455461daa2956049042840c45f774bd071d40d1931fcf0fb2 /exec failed with exit code 1
• Test CUDA Builds / unittest-cuda / linux-job (gh)
  RuntimeError: Command docker exec -t f145b4a39dae586d0e70255ee33b4396644075aa092481d436beae24cf06be27 /exec failed with exit code 2

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

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

• 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.

[larryliu0820]

Review automatically exported from Phabricator review in Meta.