Skip to content

Fix PPL increase caused by mmq_id #913

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
Nov 7, 2025
Merged

Fix PPL increase caused by mmq_id #913

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: 4 additions & 1 deletion ggml/src/ggml-cuda/mmq_id_common.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3960,7 +3960,10 @@ template <ggml_type type, int mmq_x>
static void launch_mul_mat_q_id(ggml_backend_cuda_context & ctx, const mmq_args_id & args, cudaStream_t stream) {
const int id = ggml_cuda_get_device();
const int cc = ggml_cuda_info().devices[id].cc;
const int nsm = ggml_cuda_info().devices[id].nsm;
const int nsm_max = ggml_cuda_info().devices[id].nsm;
int nsm = 1;
//while (nsm*2 <= nsm_max) nsm *= 2;
while (nsm < nsm_max) nsm *= 2;
const int warp_size = ggml_cuda_get_physical_warp_size_host(); //ggml_cuda_info().devices[id].warp_size;
const int nwarps = mmq_get_nwarps_host(cc, warp_size);
const int mmq_y = get_mmq_y_host(cc);
Expand Down