[GH-ISSUE #30] RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED #21

Closed
opened 2026-10-26 21:08:52 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @linny2002 on GitHub (Mar 14, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL/issues/30

如果用 python3.10 + CUDA11.7/CUDA11.8 + torch2.0.1,运行 inference.py 会报错如下:
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
改为 python3.8 后解决。

Originally created by @linny2002 on GitHub (Mar 14, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-VL/issues/30 如果用 python3.10 + CUDA11.7/CUDA11.8 + torch2.0.1,运行 inference.py 会报错如下: return F.conv2d(input, weight, bias, self.stride, RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED 改为 python3.8 后解决。
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-VL#21
No description provided.