From: Sigbjørn Skjæret <redacted>
Date: Wed, 10 Sep 2025 17:08:59 +0000 (+0200)
Subject: graph : support non-contiguous Q in build_attn_mha (#15908)
X-Git-Tag: upstream/0.0.6527~84
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=6ab397e12ba8e9f776341cdae68f7ffb2f8d2cde;p=pkg%2Fggml%2Fsources%2Fllama.cpp

graph : support non-contiguous Q in build_attn_mha (#15908)

* support non-contiguous Q in build_attn_mha

* Update src/llama-graph.cpp

ggml-ci

Co-authored-by: Georgi Gerganov <redacted>

---------

Co-authored-by: Georgi Gerganov <redacted>
---

diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp
index 7f254b25..ddc772b1 100644
--- a/src/llama-graph.cpp
+++ b/src/llama-graph.cpp
@@ -1273,7 +1273,7 @@ ggml_tensor * llm_graph_context::build_attn_mha(
     // split the batch into streams if needed
     const auto n_stream = k->ne[3];
 
-    q = ggml_reshape_4d(ctx0, q, q->ne[0], q->ne[1], q->ne[2]/n_stream, n_stream);
+    q = ggml_view_4d(ctx0, q, q->ne[0], q->ne[1], q->ne[2]/n_stream, n_stream, q->nb[1], q->nb[2], q->nb[3]/n_stream, 0);
 
     q = ggml_permute(ctx0, q, 0, 2, 1, 3);
     k = ggml_permute(ctx0, k, 0, 2, 1, 3);