Skip to content

Qualcomm AI Engine Direct - Fixed the wrong size for memmove in kv_manager #14685

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

Merged
merged 1 commit into from
Sep 30, 2025
Merged

Qualcomm AI Engine Direct - Fixed the wrong size for memmove in kv_manager #14685

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
6 changes: 4 additions & 2 deletions examples/qualcomm/oss_scripts/llama/runner/kv_manager.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,8 @@ void KVManager<T>::rearrange_key(KVCache<T>& k_cache, int32_t ar_len_dst) {
}
// copy from first dimension
for (int i = 0; i < metadata_.head_dim; i++) {
std::memmove(k_cache_in_write_ptr, k_cache_in_read_ptr, dst_cache_num);
std::memmove(
Copy link
Contributor

Choose a reason for hiding this comment

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

oh I see, makes sense

k_cache_in_write_ptr, k_cache_in_read_ptr, dst_cache_num * sizeof(T));
k_cache_in_read_ptr += src_cache_num;
k_cache_in_write_ptr += dst_cache_num;
}
Expand All @@ -378,7 +379,8 @@ void KVManager<T>::rearrange_key(KVCache<T>& k_cache, int32_t ar_len_dst) {
}
// copy from last dimension
for (int i = 0; i < metadata_.head_dim; i++) {
std::memmove(k_cache_in_write_ptr, k_cache_in_read_ptr, src_cache_num);
std::memmove(
k_cache_in_write_ptr, k_cache_in_read_ptr, src_cache_num * sizeof(T));
k_cache_in_read_ptr -= src_cache_num;
k_cache_in_write_ptr -= dst_cache_num;
}
Expand Down
Loading