Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	docs/backend/OPENCL.md
#	ggml/src/ggml-hexagon/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-exp.h
#	ggml/src/ggml-hexagon/htp/hvx-sigmoid.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-tool.sh
#	scripts/snapdragon/ggml-hexagon-profile.py
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2026-07-02 21:42:36 +08:00
32 changed files with 977 additions and 162 deletions
+2
View File
@@ -121,6 +121,8 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) {
res->t_layer_inp[il] = inpL;
ggml_tensor * inpSA = inpL;
cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);