Unsupported CUDA architecture: sm75 - Help

My PC Specs:
RTX 2080 8gb, i9 10900, 32 Ram.

I don't know why give-me this error when i click generate. I tried use Cuda 12.6 and 12.8 already, i'm not sure what is happening.

Can someone help-me?

Traceback (most recent call last):
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\demo_gradio.py", line 241, in worker
generated_latents = sample_hunyuan(
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\pipelines\k_diffusion_hunyuan.py", line 116, in sample_hunyuan
results = sample_unipc(k_model, latents, sigmas, extra_args=sampler_kwargs, disable=False, callback=callback)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\k_diffusion\uni_pc_fm.py", line 141, in sample_unipc
return FlowMatchUniPC(model, extra_args=extra_args, variant=variant).sample(noise, sigmas=sigmas, callback=callback, disable_pbar=disable)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\k_diffusion\uni_pc_fm.py", line 118, in sample
model_prev_list = [self.model_fn(x, vec_t)]
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\k_diffusion\uni_pc_fm.py", line 23, in model_fn
return self.model(x, t, **self.extra_args)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\k_diffusion\wrapper.py", line 37, in k_model
pred_positive = transformer(hidden_states=hidden_states, timestep=timestep, return_dict=False, **extra_args['positive'])[0].float()
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\models\hunyuan_video_packed.py", line 973, in forward
hidden_states, encoder_hidden_states = self.gradient_checkpointing_method(
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\models\hunyuan_video_packed.py", line 832, in gradient_checkpointing_method
result = block(*args)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\models\hunyuan_video_packed.py", line 652, in forward
attn_output, context_attn_output = self.attn(
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1739, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\torch\nn\modules\module.py", line 1750, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\diffusers\models\attention_processor.py", line 605, in forward
return self.processor(
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\models\hunyuan_video_packed.py", line 172, in __call__
hidden_states = attn_varlen_func(query, key, value, cu_seqlens_q, cu_seqlens_kv, max_seqlen_q, max_seqlen_kv)
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\webui\diffusers_helper\models\hunyuan_video_packed.py", line 111, in attn_varlen_func
x = sageattn(q, k, v, tensor_layout='NHD')
File "C:\Programas\StableDiffusion\FramePack\framepack_cu126_torch26\system\python\lib\site-packages\sageattention\core.py", line 138, in sageattn
raise ValueError(f"Unsupported CUDA architecture: {arch}")
ValueError: Unsupported CUDA architecture: sm75
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.

Start with webui/diffusers_helper/models/hunyuan_video_packed.py at attn_varlen_func and compare its sageattn call with system/python/lib/site-packages/sageattention/core.py at line 138. Determine whether the reported sm75 architecture is supported by this path; done means the issue has a reproducible compatibility result and a verified generation outcome or a clearly documented limitation.

Written by the indexing model from the issue text.