[GH-ISSUE #300] CUDA kernel errors #153

Open
opened 2026-10-26 21:13:45 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @ljg-ieisystem on GitHub (Apr 3, 2026).
Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/300

test_k_grouped_gemm_contiguous的测试,强行将m置为768、n置为1536。测试出现了:
torch.AcceleratorError: CUDA error: an illegal instruction was encountered
Search for cudaErrorIllegalInstruction' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information. 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
的错误。这个函数是有些shape支持不了吗?

Originally created by @ljg-ieisystem on GitHub (Apr 3, 2026). Original GitHub issue: https://github.com/deepseek-ai/DeepGEMM/issues/300 test_k_grouped_gemm_contiguous的测试,强行将m置为768、n置为1536。测试出现了: torch.AcceleratorError: CUDA error: an illegal instruction was encountered Search for `cudaErrorIllegalInstruction' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information. 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 的错误。这个函数是有些shape支持不了吗?
Sign in to join this conversation.
No labels
pull-request
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/DeepGEMM#153
No description provided.