RuntimeError: CUDA error

[dongkuang]

Please help me ! I run it in Jetson orin 64G,is aarch64

cuda_11.8.r11.8,pytorch2.0.0,show error after click "Sample"

RuntimeError: CUDA error: invalid device function Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. Traceback:

File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 552, in _run_script exec(code, module.dict) File "/home/dongkuang/generative-models/scripts/demo/sampling.py", line 318, in out = run_txt2img( File "/home/dongkuang/generative-models/scripts/demo/sampling.py", line 146, in run_txt2img out = do_sample( File "/home/dongkuang/generative-models/scripts/demo/streamlit_helpers.py", line 579, in do_sample samples_z = sampler(denoiser, randn, cond=c, uc=uc) File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/sampling.py", line 123, in call x = self.sampler_step( File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/sampling.py", line 102, in sampler_step denoised = self.denoise(x, denoiser, sigma_hat, cond, uc) File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/sampling.py", line 58, in denoise denoised = denoiser(*self.guider.prepare_inputs(x, sigma, cond, uc)) File "/home/dongkuang/generative-models/scripts/demo/streamlit_helpers.py", line 573, in denoiser return model.denoiser( File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/denoiser.py", line 28, in call return network(input * c_in, c_noise, cond) * c_out + input * c_skip File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/wrappers.py", line 28, in forward return self.diffusion_model( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/openaimodel.py", line 993, in forward h = module(h, emb, context) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/openaimodel.py", line 100, in forward x = layer(x, context) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/attention.py", line 627, in forward x = block(x, context=context[i]) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/attention.py", line 459, in forward return checkpoint( File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/util.py", line 165, in checkpoint return CheckpointFunction.apply(func, len(inputs), *args) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/autograd/function.py", line 506, in apply return super().apply(*args, **kwargs) # type: ignore[misc] File "/home/dongkuang/generative-models/sgm/modules/diffusionmodules/util.py", line 182, in forward output_tensors = ctx.run_function(*ctx.input_tensors) File "/home/dongkuang/generative-models/sgm/modules/attention.py", line 467, in _forward self.attn1( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/dongkuang/generative-models/sgm/modules/attention.py", line 355, in forward out = xformers.ops.memory_efficient_attention( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 193, in memory_efficient_attention return _memory_efficient_attention( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 291, in _memory_efficient_attention return _memory_efficient_attention_forward( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/xformers/ops/fmha/init.py", line 311, in memory_efficient_attention_forward out, * = op.apply(inp, needs_gradient=False) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/xformers/ops/fmha/flash.py", line 293, in apply out, softmax_lse, rng_state = cls.OPERATOR( File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/torch/_ops.py", line 502, in call return self._op(*args, **kwargs or {}) File "/home/dongkuang/anaconda3/envs/mystability/lib/python3.8/site-packages/xformers/ops/fmha/flash.py", line 86, in _flash_fwd ) = _C_flashattention.varlen_fwd(

[Henrik-hw]

I have the same problem，How to solve？

[ZooAtmosphereGroup]

I have the same problem with python3.11, but succeed with python3.10 !!!

[ZooAtmosphereGroup]

I have the same problem，How to solve？

I have the same problem with python3.11, but succeed with python3.10 !!!