Skip to content

npu perf fix #32

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
cavusmustafa merged 2 commits into from
Jan 12, 2026
Merged

npu perf fix #32

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5296b19
npu perf fix
cavusmustafa Jan 9, 2026
955e191
requant to f16 for Q6 embed on NPU
cavusmustafa Jan 12, 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
2 changes: 1 addition & 1 deletion ggml/src/ggml-openvino/ggml-openvino-extra.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ clEnqueueMemcpyINTEL_fn ggml_openvino_get_clEnqueueMemcpyINTEL() {
// Get requantization type for a tensor type (returns nullopt if no requant needed)
std::optional<ExtraQuantType> ggml_openvino_get_requant_type(const ggml_tensor * tensor) {
if (strncmp(tensor->name, "token_embd.weight", 17) == 0) {
return ExtraQuantType::Q8_0_C;
return ((ggml_openvino_is_npu() && tensor->type == GGML_TYPE_Q6_K) ? ExtraQuantType::F16 : ExtraQuantType::Q8_0_C);
}
if (strncmp(tensor->name, "output.weight", 13) == 0) {
return ExtraQuantType::Q8_0_C;
Expand Down