Skip to content

vulkan: disable MMVQ on AMD UMA devices #24966

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
winstonma wants to merge 1 commit into
base: master
Choose a base branch
from
+5 −0
Open

vulkan: disable MMVQ on AMD UMA devices #24966

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
5 changes: 5 additions & 0 deletions ggml/src/ggml-vulkan/ggml-vulkan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8777,6 +8777,11 @@ static bool ggml_vk_should_use_mmvq(const vk_device& device, uint32_t m, uint32_
if (k < 2048) {
return false;
}
// On UMA, MMVQ's quantization overhead outweighs bandwidth savings
// because CPU and GPU share the same memory pool.
if (device->uma) {
return false;
}

switch (src0_type) {
case GGML_TYPE_Q8_0:
Expand Down