ChatGLM-6B icon indicating copy to clipboard operation
ChatGLM-6B copied to clipboard

[RuntimeError] <CUDA error: an illegal memory access was encountered>

Open Dhaizei opened this issue 3 years ago • 2 comments

Is your feature request related to a problem? Please describe.

RuntimeError: CUDA error: an illegal memory access was encountered 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.

Solutions

我仅仅是 让这个模型一直运行,没有存储历史数据,用了两张卡来运行的。怎么解决?

Additional context

No response

Dhaizei avatar Apr 26 '23 01:04 Dhaizei

mark , same problem , have you find a solution ? @Dhaizei

leoluopy avatar Oct 25 '23 15:10 leoluopy

i give up. you can try fastchat to use this model

Dhaizei avatar Oct 25 '23 16:10 Dhaizei