Skip to content

Fix CMakeLists.txt and conv_transpose_kernel_impl.h #2338

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
YuhanXu wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

Fix CMakeLists.txt and conv_transpose_kernel_impl.h #2338

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5e430f5
Fix CMakeLists.txt and conv_transpose_kernel_impl.h
YuhanXu Jan 12, 2026
cc3403b
Merge branch 'develop' into fix_cmakelists_cfo
metax666 Jan 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion backends/metax_gpu/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -797,8 +797,13 @@ target_compile_definitions(
${TARGET_NAME}
PUBLIC PADDLE_WITH_CUDA=1
PADDLE_WITH_CUSTOM_DEVICE=1
mcblasContext=cublasContext
cublasContext=mcblasContext
cublasLtContext=mcblasLtContext
cublasLtMatmulDescOpaque_t=mcblasLtMatmulDescOpaque_t
cublasLtMatrixLayoutOpaque_t=mcblasLtMatrixLayoutOpaque_t
cublasLtMatmulPreferenceOpaque_t=mcblasLtMatmulPreferenceOpaque_t
cublasLtMatmulAlgoOpaque_t=mcblasLtMatmulAlgoOpaque_t
cublasStatus_t=mcblasStatus_t
GPUContext=CustomContext
KPSContext=CustomContext
STREAM_TYPE=cudaStream_t
Expand Down
3 changes: 1 addition & 2 deletions backends/metax_gpu/kernels/impl/conv_transpose_kernel_impl.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,8 +142,7 @@ void ConvTransposeRawKernel(const Context& dev_ctx,
(data_layout != DataLayout::kNHWC
? static_cast<int>(out_dims[1]) / groups
: static_cast<int>(out_dims[out_dims.size() - 1]) / groups);
phi::funcs::Col2ImFunctor<phi::funcs::ColFormat::kCFO, Context, T> col2im;
phi::funcs::Col2VolFunctor<Context, T> col2vol;
phi::funcs::Col2ImFunctor<phi::funcs::ColFormat::CFO, Context, T> col2im;
funcs::ConcatFunctor<Context, T> concat_functor;

// convolution transpose: gemm + col2im or col2vol (similar to conv-backward
Expand Down
Loading