[Bug]: Flux 2 will not run just gives killed on a strix halo rocm .

### ComfyUI and Frontend Versions

Will that a first , no error out of memory , error do to compiled error etc , just a killed .
I'm on the latest 0.3.75 version ,all other workflow work but some times very slow ,
it goes as far as sampler custom advanced .

got prompt
Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load AutoencoderKL
loaded completely; 55507.90 MB usable, 160.31 MB loaded, full load: True
Requested to load Flux2TEModel_
loaded completely; 95367431640625005117571072.00 MB usable, 33080.59 MB loaded, full load: True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
Found quantization metadata (version 1.0)
Detected mixed precision quantization: 128 layers quantized
Using mixed precision operations: 128 quantized layers
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
Requested to load Flux2
loaded partially: 20160.00 MB loaded, lowvram patches: 0
Killed

### Description

t goes as far as sampler custom advanced , and is killed

### Steps to Reproduce

does it every time on flux 2 on my set up.

### Debug Logs

```powershell
got prompt
Using split attention in VAE
Using split attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Requested to load AutoencoderKL
loaded completely; 55507.90 MB usable, 160.31 MB loaded, full load: True
Requested to load Flux2TEModel_
loaded completely; 95367431640625005117571072.00 MB usable, 33080.59 MB loaded, full load: True
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cuda:0, dtype: torch.float16
Found quantization metadata (version 1.0)
Detected mixed precision quantization: 128 layers quantized
Using mixed precision operations: 128 quantized layers
model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
model_type FLUX
Requested to load Flux2
loaded partially: 20160.00 MB loaded, lowvram patches: 0
Killed
```

### Browser Logs

no browser log .

### Setting JSON

{
"LiteGraph.Canvas.MinFontSizeForLOD": 8,
"Comfy.VueNodes.Enabled": false,
"Comfy.Minimap.Visible": false
}

### What browsers do you use to access the UI ?

Google Chrome