Skip to content

CUDA: only use moe_expert_reduce when n_tokens=1 #17032

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
wants to merge 1 commit into
base: master
Choose a base branch
from
+6 −1
Open

CUDA: only use moe_expert_reduce when n_tokens=1 #17032

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
7 changes: 6 additions & 1 deletion ggml/src/ggml-cuda/moe-expert-reduce.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,12 @@ static void launch_moe_expert_reduce(ggml_backend_cuda_context & ctx,
}

bool ggml_cuda_should_use_moe_expert_reduce(const ggml_cgraph * cgraph, int start_index, int end_index) {
const ggml_tensor * mul = cgraph->nodes[start_index];
const ggml_tensor * mul = cgraph->nodes[start_index];
const ggml_tensor * experts = mul->src[0];

if (experts->ne[2] != 1) {
return false;
}

if (mul->op != GGML_OP_MUL || !ggml_is_contiguous(mul->src[0]) || !ggml_is_contiguous(mul->src[1])) {
return false;
Expand Down
Loading