tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/bitnet-ternary

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-08-13 17:36:09 -04:00
parent 69f772682e 06943a69f6
commit 82b240406d
22 changed files with 75 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/include/ggml.h
View File

@@ -244,6 +244,8 @@
#define GGML_EXIT_SUCCESS 0
#define GGML_EXIT_ABORTED 1
#define GGML_ROPE_TYPE_NEOX 2
#define GGUF_MAGIC "GGUF"
#define GGUF_VERSION 3
@@ -1455,8 +1457,8 @@ extern "C" {
struct ggml_tensor * b);
// rotary position embedding
// if mode & 1 == 1, skip n_past elements (NOT SUPPORTED)
// if mode & 2 == 1, GPT-NeoX style
// if (mode & 1) - skip n_past elements (NOT SUPPORTED)
// if (mode & GGML_ROPE_TYPE_NEOX) - GPT-NeoX style
//
// b is an int32 vector with size a->ne[2], it contains the positions
GGML_API struct ggml_tensor * ggml_rope(