E2E on AWS CUDA Not finding devices

[Alcpz]

Describe the bug

E2E on AWS CUDA is currently failing for multiple PRs because the runner doesn't seem to detect a CUDA device.

Run ninja -C build-e2e check-sycl-e2e > e2e.log 2>&1
ninja: Entering directory `build-e2e'
[0/1] Running SYCL End-to-End tests
lit.py: /__w/llvm/llvm/llvm/sycl/test-e2e/lit.cfg.py:412: note: Targeted devices: ext_oneapi_cuda:gpu
lit.py: /__w/llvm/llvm/llvm/sycl/test-e2e/lit.cfg.py:580: warning: Couldn't find pre-installed AOT device compiler ocloc
lit.py: /__w/llvm/llvm/llvm/sycl/test-e2e/lit.cfg.py:577: note: Found pre-installed AOT device compiler opencl-aot
lit.py: /__w/llvm/llvm/llvm/sycl/test-e2e/lit.cfg.py:599: note: Kernel fusion extension enabled
lit.py: /__w/llvm/llvm/llvm/sycl/test-e2e/lit.cfg.py:665: error: Cannot detect device aspect for cuda:gpu
stdout:

Platforms: 0
default_selector()      : No device of requested type available. -1 (PI_ERRO...
accelerator_selector()  : No device of requested type available. -1 (PI_ERRO...
cpu_selector()          : No device of requested type available. -1 (PI_ERRO...
gpu_selector()          : No device of requested type available. -1 (PI_ERRO...
custom_selector(gpu)    : No device of requested type available. -1 (PI_ERRO...
custom_selector(cpu)    : No device of requested type available. -1 (PI_ERRO...
custom_selector(acc)    : No device of requested type available. -1 (PI_ERRO...

To reproduce

Run E2E on AWS CUDA action

Environment

No response

Additional context

No response

[Alcpz]

Example log: https://github.com/intel/llvm/actions/runs/9394120038

[KornevNikita]

FYI @aelovikov-intel

[JackAKirk]

I think it is due to #14049
Will point back the docker image to the previous commit.

[JackAKirk]

This points to the docker from the previous commit, and should fix these failures #14074