Commit 5cdadfc32 for llama.cpp

commit 5cdadfc326163ed1fa66cf609fb1761f7928900c
Author: Aman Gupta <amangupta052@gmail.com>
Date:   Wed Oct 14 21:01:53 2026 +0530

    ggml-cpu : size set_rows conversion buffer for all threads (#30454)

    * ggml-cpu : size set_rows conversion buffer for all threads

    SET_ROWS is planned with n_tasks = 1, but every thread runs it and uses its own row of the F16 -> F32 conversion buffer, so threads > 0 wrote past the work buffer when the graph had another multi-threaded op.

    * move set_rows to n_task = n_threads group

diff --git a/ggml/src/ggml-cpu/ggml-cpu.c b/ggml/src/ggml-cpu/ggml-cpu.c
index 5428d5164..ab82e3d6c 100644
--- a/ggml/src/ggml-cpu/ggml-cpu.c
+++ b/ggml/src/ggml-cpu/ggml-cpu.c
@@ -2360,11 +2360,11 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) {
         case GGML_OP_MUL_MAT:
         case GGML_OP_MUL_MAT_ID:
         case GGML_OP_OUT_PROD:
+        case GGML_OP_SET_ROWS:
             {
                 n_tasks = n_threads;
             } break;
         case GGML_OP_GET_ROWS:
-        case GGML_OP_SET_ROWS:
             {
                 // FIXME: get_rows can use additional threads, but the cost of launching additional threads
                 // decreases performance with GPU offloading