LLM inference in C/C++
C++ ggml
mtmd/ggml: add ggml_build_forward_order (#26649)
Pascalc8e03ce8122b
diff --git a/ggml/include/ggml.h b/ggml/include/ggml.hindex 35f0c44ec4..5cb49d0ee4 100644--- a/ggml/include/ggml.h+++ b/ggml/include/ggml.h@@ -2788,6 +2788,12 @@ extern "C" {struct ggml_cgraph * cgraph,struct ggml_tensor * tensor);+ // add the tensor and its parents to the graph without marking them for compute+ // the flag is set later, when the tensor is reached from a node that computes+ GGML_API void ggml_build_forward_order(+ struct ggml_cgraph * cgraph,+ struct ggml_tensor * tensor);+GGML_API void ggml_build_backward_expand(struct ggml_context * ctx, // context for gradient computationstruct ggml_cgraph * cgraph,diff --git a/ggml/src/ggml.c b/ggml/src/ggml.cindex 59191c663e..da7f3a5f2e 100644--- a/ggml/src/ggml.c+++ b/ggml/src/ggml.c@@ -7200,6 +7200,10 @@ void ggml_build_forward_expand(struct ggml_cgraph * cgraph, struct ggml_tensor *ggml_build_forward_impl(cgraph, tensor, true, true);}+void ggml_build_forward_order(struct ggml_cgraph * cgraph, struct ggml_tensor * tensor) {+ ggml_build_forward_impl(cgraph, tensor, true, false);+}+void ggml_build_backward_expand(struct ggml_context * ctx,struct ggml_cgraph * cgraph,diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cppindex c77e7cc9d3..b1360fd7d3 100644--- a/tools/mtmd/clip.cpp+++ b/tools/mtmd/clip.cpp@@ -708,9 +708,10 @@ ggml_tensor * clip_graph::build_attn(ggml_tensor * sinks) const {// these nodes are added to the graph together so that they are not reordered// by doing so, the number of splits in the graph is reduced- ggml_build_forward_expand(gf, q_cur);- ggml_build_forward_expand(gf, k_cur);- ggml_build_forward_expand(gf, v_cur);+ // the order is fixed without the compute flag, so an unselected branch stays out of the compute set+ ggml_build_forward_order(gf, q_cur);+ ggml_build_forward_order(gf, k_cur);+ ggml_build_forward_order(gf, v_cur);ggml_tensor * q = ggml_permute(ctx0, q_cur, 0, 2, 1, 3);//cb(q, "q", il);