CUDA error: no kernel image is available for execution on the device

[a912289748]

[Weishangbin]

No description provided.

你好请问你解决这个问题了吗

[Shubham]

Could you provide the full error message? I had the same issue and it because triton was compiled with a different CUDA version compared to mamba_ssm

Compiling both from scratch on my device solved the issue

[ZXXaaaa]

Could you provide the full error message? I had the same issue and it because triton was compiled with a different CUDA version compared to mamba_ssm

Compiling both from scratch on my device solved the issue

this is my error
CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Can you help me? thx

[ZXXaaaa]

No description provided.

你好请问你解决这个问题了吗

Have you solved it?

[zjy-2020]

Could you provide the full error message? I had the same issue and it because triton was compiled with a different CUDA version compared to mamba_ssm
Compiling both from scratch on my device solved the issue

this is my error CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. Can you help me? thx

Hello, I have encountered the same problem, have you solved it?

[zjy-2020]

你能提供完整的错误消息吗？我遇到了同样的问题，因为与triton``mamba_ssm

在我的设备上从头开始编译两者解决了这个问题
Hello, I have encountered the same problem, have you solved it?

[ZXXaaaa]

Could you provide the full error message? I had the same issue and it because triton was compiled with a different CUDA version compared to mamba_ssm
Compiling both from scratch on my device solved the issue

this is my error CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. Can you help me? thx

Hello, I have encountered the same problem, have you solved it?

Yes, I solved it by renting a more powerful server with better GPU

[you said life]

Regarding the computing power of NVIDIA graphics cards, the minimum requirement is 70