From a1a5508d67a7c38905e230ee0ffcf088a8e7b477 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stanis=C5=82aw=20Szymczyk?= Date: Wed, 22 May 2024 15:52:10 +0200 Subject: [PATCH] llama : Replaced obsolete ggml_rope_custom() calls with ggml_rope_ext(). --- llama.cpp | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/llama.cpp b/llama.cpp index d5f346043..452cf4647 100644 --- a/llama.cpp +++ b/llama.cpp @@ -10707,15 +10707,15 @@ struct llm_build_context { struct ggml_tensor * Vcur = ggml_mul_mat(ctx0, model.layers[il].wv, cur); cb(Vcur, "Vcur", il); - Qcur = ggml_rope_custom( - ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, + Qcur = ggml_rope_ext( + ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, nullptr, n_rot, rope_type, 0, n_orig_ctx, freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow ); cb(Qcur, "Qcur", il); - Kcur = ggml_rope_custom( - ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos, + Kcur = ggml_rope_ext( + ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos, nullptr, n_rot, rope_type, 0, n_orig_ctx, freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow );