Commit f266648fa for llama.cpp

commit f266648fa9ef20b4332226c6fda14fffb85a3002
Author: I3eg1nner <45710049+I3eg1nner@users.noreply.github.com>
Date:   Wed Sep 16 19:19:47 2026 +0800

    spacemit : fix wrong transpose function for int16 data (#25161)

    The `sizeof(int16_t)` branch in `permute_transpose_impl` calls
    `rvv_transposed_s32_mn_to_nm` instead of `rvv_transposed_s16_mn_to_nm`.
    This is a copy-paste bug from the `sizeof(int32_t)` branch above it.

    The s32 function uses 32-bit segment load/stores (`vssseg8e32.v`) on 16-bit
    data, reading 2x bytes per element and producing completely wrong
    transposition results -- 14 out of 16 positions are corrupted for a 4x4
    int16 matrix.

    The correct function `rvv_transposed_s16_mn_to_nm` already exists (line 390)
    and is used elsewhere in flash attention (line 1488).

diff --git a/ggml/src/ggml-cpu/spacemit/rvv_kernels.cpp b/ggml/src/ggml-cpu/spacemit/rvv_kernels.cpp
index d2f897436..13b84dcbe 100644
--- a/ggml/src/ggml-cpu/spacemit/rvv_kernels.cpp
+++ b/ggml/src/ggml-cpu/spacemit/rvv_kernels.cpp
@@ -639,7 +639,7 @@ static void permute_transpose_impl(const ggml_tensor * src0,
         }
     } else if (n_src_stride == sizeof(int16_t)) {
         for (int64_t bi = ith; bi < batch; bi += nth) {
-            rvv_transposed_s32_mn_to_nm((int8_t *) ((char *) dst->data + bi * batch_stride), n_dst_stride,
+            rvv_transposed_s16_mn_to_nm((int8_t *) ((char *) dst->data + bi * batch_stride), n_dst_stride,
                                         (int8_t *) ((char *) src0->data + bi * batch_stride), m_src_stride, m, n);
         }
     } else {