Merge commit '961e4b26a7dd0e01e20599b27d709a74788ecb55' into concedo_experimental

# Conflicts:
#	.github/workflows/hip-quality-check.yml
#	AGENTS.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-hexagon/htp/hmx-fa-kernels.h
#	ggml/src/ggml-hexagon/htp/hmx-queue.c
#	ggml/src/ggml-hexagon/htp/hmx-queue.h
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/worker-pool.c
#	ggml/src/ggml-hexagon/htp/worker-pool.h
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q4_0.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q8_0.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_mxfp4_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q4_0_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q4_1_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q4_k_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q5_0_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q5_1_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q5_k_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q6_k_f32_ns.cl
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/cli/CMakeLists.txt
#	tools/cli/cli.cpp
#	tools/llama-bench/llama-bench.cpp

src/llama-graph.cpp

@@ -1193,6 +1193,7 @@ void llm_graph_result::reset() {
     params = {};
 
     inputs.clear();
+    fused_nodes.clear();
 
     buf_compute_meta.resize(ggml_tensor_overhead()*max_nodes + ggml_graph_overhead_custom(max_nodes, false));
 
@@ -1294,6 +1295,10 @@ llm_graph_input_i * llm_graph_result::add_input(llm_graph_input_ptr input) {
     return inputs.back().get();
 }
 
+void llm_graph_result::add_fused_node(llm_graph_fused_node result) {
+    fused_nodes.push_back(result);
+}
+
 void llm_graph_result::set_params(const llm_graph_params & params) {
     this->params = params;
 }
@@ -1353,6 +1358,8 @@ void llm_graph_context::cb(ggml_tensor * cur, const char * name, int il) const {
     }
 }
 
+
+
 ggml_tensor * llm_graph_context::build_cvec(
          ggml_tensor * cur,
                  int   il) const {
@@ -2403,7 +2410,7 @@ ggml_tensor * llm_graph_context::build_attn_mha(
 
         cur = ggml_flash_attn_ext(ctx0, q, k, v, kq_mask, kq_scale, hparams.f_max_alibi_bias,
                                   hparams.attn_soft_cap ? hparams.f_attn_logit_softcapping : 0.0f);
-        cb(cur, LLAMA_TENSOR_NAME_FATTN, il);
+        res->add_fused_node({LLM_FUSED_OP_FLASH_ATTN, cur, il});
 
         ggml_flash_attn_ext_add_sinks(cur, sinks);
         ggml_flash_attn_ext_set_prec (cur, GGML_PREC_F32);