upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-06 10:00:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

mtmd/ggml: add ggml_build_forward_order (#26649)

Browse Source 
* ggml: add ggml_build_forward_order

ggml_build_forward_expand marks the tensor and all its ancestors for
compute, so using it as a pure ordering hint (keeping q, k and v
together) defeats ggml_build_forward_select: the unselected branch is
forced to run with inputs that were never uploaded. In the mtmd audio
graph this makes GEN_WAV calls execute the GEN_CODE branch with a
stale inp_code0, hitting the get_rows bound assert on CPU.

Add ggml_build_forward_order, which inserts nodes without the compute
flag; the flag is restored when the branch is actually selected.
Switch the q/k/v hints in clip_graph::build_attn to it.

* nit: reduce comments (AGENTS.md)
This commit is contained in:
Pascal
2026-08-06 00:47:59 +02:00
committed by GitHub
parent f9e832c10e
commit c8e03ce812
3 changed files with 14 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/include/ggml.h
View File

@@ -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 computation
struct ggml_cgraph * cgraph,

4
ggml/src/ggml.c
View File

@@ -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,

7
tools/mtmd/clip.cpp
View File

@@ -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);