Skip to content

Heuristics for mmq_id -> original threshold #734

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
ikawrakow merged 1 commit into from
Aug 27, 2025
Merged

Heuristics for mmq_id -> original threshold #734

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
10 changes: 9 additions & 1 deletion ggml/src/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2681,7 +2681,15 @@ static bool ggml_cuda_up_gate_unary(ggml_backend_cuda_context & ctx, ggml_tensor

ggml_tensor dst_row = *dst;

if (src1->ne[2] <= 2048 && // TODO: this depends on number of total vs number of active experts -> need to find optimum threshod
// The heuristics src1->ne[2] <= 32*src0->ne[2] to use the mul_mat_id implementation instead of the original version
// is derived from
// * DeepSeek-Lite: 64 total, 6 active experts
// * GPT-OSS-20B : 32 total, 4 active experts
// * Qwen3-30B-A3B: 128 total, 8 active experts
// My original hypothesis was that it is dependent on the total/active experts ratio, but from these 3 it
// looks like it really depends just on the total number of experts.
// TODO: verify with more models, or perhaps make the magic constant '32' to be defined via a compile time define.
if (src1->ne[2] <= 32*src0->ne[2] &&
ggml_is_quantized(src0_1->type) && src0_1->type == src0_2->type && src1->ne[1] == 1 && src1->ne[3] == 1 &&
ggml_cuda_can_use_mmq_id(src0_1->type, ggml_cuda_info().devices[ctx.device].cc, src1->ne[2])) {

Expand Down