diff --git a/src/models/glm5next.cpp b/src/models/glm5next.cpp
index 98922645fd4e..5b617c02b07e 100644
--- a/src/models/glm5next.cpp
+++ b/src/models/glm5next.cpp
@@ -383,7 +383,9 @@ ggml_tensor * llama_model_glm5next::graph::build_indexer(
     ggml_tensor * ape = ggml_cont(ctx0, ggml_transpose(ctx0, layer.indexer_comp_ape));
     gate_t = ggml_add(ctx0, gate_t, ggml_reshape_4d(ctx0, ape, r, d_idx, 1, 1));
 
-    ggml_tensor * probs = ggml_soft_max(ctx0, gate_t);
+    // soft_max maps ne2/ne3 to gridDim.y/z (65535 cap); fold into ne1
+    ggml_tensor * probs = ggml_soft_max(ctx0, ggml_reshape_2d(ctx0, gate_t, r, d_idx*n_new_max*n_stream));
+    probs = ggml_reshape_4d(ctx0, probs, r, d_idx, n_new_max, n_stream);
     cb(probs, "indexer_pool_probs", il);
 
     ggml_tensor * pool_new = ggml_sum_rows(ctx0, ggml_mul(ctx0, keys_t, probs));