diff --git a/ggml.c b/ggml.c index 8bfb9531e..5025ec23b 100644 --- a/ggml.c +++ b/ggml.c @@ -6392,6 +6392,16 @@ struct ggml_tensor * ggml_rope_custom_inplace( ); } +struct ggml_tensor * ggml_rope_xpos_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b, + int n_dims, + float base, + bool down) { + return ggml_rope_impl(ctx, a, b, NULL, n_dims, 0, 0, 0, 10000.0f, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f, base, down, true); +} + // ggml_rope_back struct ggml_tensor * ggml_rope_back( diff --git a/ggml.h b/ggml.h index 4e6bcb30f..3859895b6 100644 --- a/ggml.h +++ b/ggml.h @@ -1548,6 +1548,14 @@ extern "C" { float beta_slow), "use ggml_rope_ext_inplace instead"); + struct ggml_tensor * ggml_rope_xpos_inplace( + struct ggml_context * ctx, + struct ggml_tensor * a, + struct ggml_tensor * b, + int n_dims, + float base, + bool down); + // compute correction dims for YaRN RoPE scaling GGML_CALL void ggml_rope_yarn_corr_dims( int n_dims, int n_orig_ctx, float freq_base, float beta_fast, float beta_slow, float dims[2]);