Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : move c parameter comment to ggml_rope_ext (ggml/901)

Browse Source 
This commit moves the comment for the c parameter from ggml_rope to
ggml_rope_ext. The comment is currently incorrect as ggml_rope does not
have a c parameter (freq_factors tensor).

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
This commit is contained in:
Daniel Bevenius 2024-07-29 15:06:06 +02:00 committed by Georgi Gerganov
parent c02b0a8a4d
commit 655858ace0
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml.h
View File

@ -1456,7 +1456,6 @@ extern "C" {
// if mode & 2 == 1, GPT-NeoX style
//
// b is an int32 vector with size a->ne[2], it contains the positions
// c is freq factors (e.g. phi3-128k), (optional)
GGML_API struct ggml_tensor * ggml_rope(
struct ggml_context * ctx,
struct ggml_tensor * a,
@ -1473,6 +1472,7 @@ extern "C" {
int mode);
// custom RoPE
// c is freq factors (e.g. phi3-128k), (optional)
GGML_API struct ggml_tensor * ggml_rope_ext(
struct ggml_context * ctx,
struct ggml_tensor * a,