diff options
| -rw-r--r-- | llama.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -5523,8 +5523,8 @@ static void llm_build_kv_store( GGML_ASSERT(kv.size == n_ctx); // compute the transposed [n_tokens, n_embd] V matrix - struct ggml_tensor * v_cur_t = ggml_transpose(ctx, ggml_reshape_2d(ctx, v_cur, n_embd_v_gqa, n_tokens)); - //struct ggml_tensor * v_cur_t = ggml_transpose(ctx, v_cur); // TODO: reshape above is likely not needed + assert(v_cur->ne[0] == n_embd_v_gqa && v_cur->ne[1] == n_tokens); + struct ggml_tensor * v_cur_t = ggml_transpose(ctx, v_cur); cb(v_cur_t, "v_cur_t", il); struct ggml_tensor * k_cache_view = ggml_view_1d(ctx, kv.k_l[il], n_tokens*n_embd_k_gqa, |