happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model: fix qwen3next broken due to #18683 (#18762)

This commit is contained in:
Xuan-Son Nguyen 2026-01-11 21:00:10 +01:00 committed by GitHub
parent 0e76501e1d
commit 0c3b7a9efe
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/models/qwen3next.cpp
View File

@ -590,6 +590,7 @@ std::pair<ggml_tensor *, ggml_tensor *> llm_build_qwen3next::build_qkvz(
ggml_tensor * z = ggml_view_4d(ctx0, mixed_qkvz_reshaped, split_sizes_qkvz[3], num_k_heads, n_seq_tokens, n_seqs,
mixed_qkvz_reshaped->nb[1], mixed_qkvz_reshaped->nb[2], mixed_qkvz_reshaped->nb[3],
(split_sizes_qkvz[0] + split_sizes_qkvz[1] + split_sizes_qkvz[2]) * ggml_element_size(mixed_qkvz_reshaped));
z = ggml_cont(ctx0, z);
cb(z, "z", il);
// After creating query, key, and value_reshaped, reshape each to flatten the head dimensions