Skip to content

CANN: fix ggml_cann_rms_norm #15331

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

Closed
wants to merge 1 commit into from
+2 −1
Closed

CANN: fix ggml_cann_rms_norm #15331

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion ggml/src/ggml-cann/aclnn_ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -885,9 +885,10 @@ void ggml_cann_rms_norm(ggml_backend_cann_context& ctx, ggml_tensor* dst) {
size_t zero_tensor_n_bytes =
src->ne[1] * src->ne[2] * src->ne[3] * ggml_element_size(src);
ggml_cann_pool_alloc zero_tensor_allocator(ctx.pool(), zero_tensor_n_bytes);
int64_t rstd_ne[GGML_MAX_DIMS] = {src->ne[1] , src->ne[2] , src->ne[3] , 1};
aclTensor* acl_rstd =
aclnn_zero(ctx, zero_tensor_allocator.get(), zero_tensor_n_bytes,
src->ne, GGML_MAX_DIMS, ggml_cann_type_mapping(src->type),
rstd_ne, 3, ggml_cann_type_mapping(src->type),
Copy link
Collaborator

@hipudding hipudding Aug 20, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you can just change GGML_MAX_DIMS to GGML_MAX_DIMS-1, and rstd_ne is not needed. aclnn_zero will only use acl_rstd as a 3-dim tensor.

Copy link
Contributor Author

@yuchuan-cao yuchuan-cao Aug 20, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Indeed, thanks! I suppose #15419 would better fix this issue.

ggml_element_size(src));
GGML_CANN_CALL_ACLNN_OP(ctx, RmsNorm, acl_src, acl_gamma, eps, acl_dst, acl_rstd);
ggml_cann_release_resources(ctx, acl_src, acl_dst, acl_gamma, acl_rstd);
Expand Down
Loading