upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-02 19:07:25 -05:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: enable sparse fa for qwen4

Browse Source
This commit is contained in:
Aman Gupta
2026-09-11 23:06:46 +08:00
parent 4d9176092d
commit 41a4ad00dd
5 changed files with 68 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/models/qwen4exp.cpp
+1 -4
View File
@@ -744,10 +744,7 @@ 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);
// TODO: enable sparse attention when we are ready
// ref: https://github.com/ggml-org/llama.cpp/pull/27970
//ggml_tensor * cur = build_attn_mha(q, k, v, nullptr, kq_mask_top_k, nullptr, nullptr, top_k->ne[0], kq_scale, 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