vulkan: Split large mul_mat_id to fit in shared memory (ggml-org#14451)

Author: jeffbolznv

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -10161,9 +10161,15 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
                 ggml_type src0_type = op->src[0]->type;
                 ggml_backend_vk_device_context * ctx = (ggml_backend_vk_device_context *)dev->context;
                 const vk_device& device = ggml_vk_get_device(ctx->device);
-                if (op->op == GGML_OP_MUL_MAT_ID && !device->mul_mat_id_s[src0_type] && !device->mul_mat_id_m[src0_type] && !device->mul_mat_id_l[src0_type]) {
-                    // If there's not enough shared memory for row_ids and the result tile, fallback to CPU
-                    return false;
+                if (op->op == GGML_OP_MUL_MAT_ID) {
+                    if (!device->mul_mat_id_s[src0_type] && !device->mul_mat_id_m[src0_type] && !device->mul_mat_id_l[src0_type]) {
+                        // If there's not enough shared memory for row_ids and the result tile, fallback to CPU
+                        return false;
+                    }
+                    // Check against size of shared memory variable
+                    if (op->src[2]->ne[0] > 4096) {
+                        return false;
+                    }
                 }
                 switch (src0_type) {
                     case GGML_TYPE_F32: