You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Just to report right now two test cases test-conv1d and test-conv2d cannot pass if running on GPU backend and its computation capability <= 6.1. On a GTX 1070 with CUDA version 12.1, it gave
ggml_im2col (4320): PASSED
ggml_conv2d (480): FAILED
The text was updated successfully, but these errors were encountered:
bssrdf
changed the title
test-conv2d failed on GPUs with computation capability <= 6.1
test-conv1d and test-conv2d failed on GPUs with computation capability <= 6.1
Dec 28, 2023
Just to report right now two test cases
test-conv1d
andtest-conv2d
cannot pass if running on GPU backend and its computation capability <= 6.1. On a GTX 1070 with CUDA version 12.1, it gaveggml_im2col (4320): PASSED
ggml_conv2d (480): FAILED
This might be related to this section of the code
ggml/src/ggml-cuda.cu
Lines 7618 to 7639 in 3d57e76
Here
src1
is not converted to FP32 whilesrc0
is.The text was updated successfully, but these errors were encountered: