Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 09:15:04 +02:00
Code Issues Packages Projects Releases Wiki Activity

qwen4 : enable sparse attention

Browse Source
This commit is contained in:
Georgi Gerganov
2026-08-31 18:32:20 +03:00
parent 25d5a86645
commit 70ed98962d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/qwen4exp.cpp
+1 -1
View File
@@ -686,7 +686,7 @@ ggml_tensor * llama_model_qwen4exp::graph::build_attn_qsa(
ggml_tensor * k = mctx_cur->get_k(ctx0, il);
ggml_tensor * v = mctx_cur->get_v(ctx0, il);
ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, 0, kq_scale, il);
ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, top_k->ne[0], kq_scale, il);
cb(cur, "kqv_out", il);
// the rotation is its own inverse, so undo it on the value side of the output