Skip to content

Override SSM_A op for Qwen3 Next to reduce splits #17587

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
+4 −0
Open

Override SSM_A op for Qwen3 Next to reduce splits #17587

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
Override SSM_A op for Qwen3 Next to reduce splits
  • Loading branch information
@pwilkin
pwilkin committed Nov 29, 2025
commit 0a60230caec724f427f48692b0a6fdf737962445
4 changes: 4 additions & 0 deletions src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2437,6 +2437,10 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
throw std::runtime_error(format("missing tensor info mapping for %s", tn.str().c_str()));
}

if (arch == LLM_ARCH_QWEN3NEXT && tn_tensor == LLM_TENSOR_SSM_A) {
info.op = GGML_OP_MUL; // override SSM_SCAN default
}

// skip unused tensors
if (info.op == GGML_OP_NONE || flags & TENSOR_SKIP) {
const size_t nbytes = ggml_nbytes(t_meta);
Expand Down
Loading