Skip to content

Commit

Permalink
llama : Replaced obsolete ggml_rope_custom() calls with ggml_rope_ext().
Browse files Browse the repository at this point in the history
  • Loading branch information
sszymczy committed May 22, 2024
1 parent eb58c4b commit a1a5508
Showing 1 changed file with 4 additions and 4 deletions.
8 changes: 4 additions & 4 deletions llama.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -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
);
Expand Down

0 comments on commit a1a5508

Please sign in to comment.