Launch failed on AMD RDNA3.5 Strix Halo gfx1151

### Custom Node Testing

- [ ] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

Launch comfyui successfully

### Actual Behavior

``` terminal
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ pip list | grep torch
pytorch-triton-rocm 3.5.0+git914d08f2.rocm7.10.0a20251015
torch 2.10.0a0+rocm7.10.0a20251015
torchaudio 2.9.0+rocm7.11.0a20251216
torchsde 0.2.6
torchvision 0.25.0a0+rocm7.10.0a20251015
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ python main.py --port 8888
Checkpoint files will always be loaded safely.
Total VRAM 131072 MB, total RAM 124418 MB
pytorch version: 2.10.0a0+rocm7.10.0a20251015
Set: torch.backends.cudnn.enabled = False for better AMD performance.
AMD arch: gfx1151
ROCm version: (7, 1)
Set vram state to: NORMAL_VRAM
Device: cuda:0 Radeon 8060S Graphics : native
Using async weight offloading with 2 streams
Enabled pinned memory 118196.0
Using pytorch attention
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)
```

### Steps to Reproduce

# Installation

``` sh
pip install --pre torch torchvision torchaudio --index-url https://rocm.nightlies.amd.com/v2/gfx1151/

pip install -r requirement.txt
```

# Run

``` terminal
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ pip list | grep torch
pytorch-triton-rocm 3.5.0+git914d08f2.rocm7.10.0a20251015
torch 2.10.0a0+rocm7.10.0a20251015
torchaudio 2.9.0+rocm7.11.0a20251216
torchsde 0.2.6
torchvision 0.25.0a0+rocm7.10.0a20251015
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ python main.py --port 8888
Checkpoint files will always be loaded safely.
Total VRAM 131072 MB, total RAM 124418 MB
pytorch version: 2.10.0a0+rocm7.10.0a20251015
Set: torch.backends.cudnn.enabled = False for better AMD performance.
AMD arch: gfx1151
ROCm version: (7, 1)
Set vram state to: NORMAL_VRAM
Device: cuda:0 Radeon 8060S Graphics : native
Using async weight offloading with 2 streams
Enabled pinned memory 118196.0
Using pytorch attention
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)
```

### Debug Logs

```powershell
terminal
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ pip list | grep torch
pytorch-triton-rocm 3.5.0+git914d08f2.rocm7.10.0a20251015
torch 2.10.0a0+rocm7.10.0a20251015
torchaudio 2.9.0+rocm7.11.0a20251216
torchsde 0.2.6
torchvision 0.25.0a0+rocm7.10.0a20251015
(comfyui) alex@GZ302EA:~/ComfyUI/ComfyUI$ python main.py --port 8888
Checkpoint files will always be loaded safely.
Total VRAM 131072 MB, total RAM 124418 MB
pytorch version: 2.10.0a0+rocm7.10.0a20251015
Set: torch.backends.cudnn.enabled = False for better AMD performance.
AMD arch: gfx1151
ROCm version: (7, 1)
Set vram state to: NORMAL_VRAM
Device: cuda:0 Radeon 8060S Graphics : native
Using async weight offloading with 2 streams
Enabled pinned memory 118196.0
Using pytorch attention
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)
```

### Other

_No response_