alihan/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2023-11-04 02:52:44 +03:00
Code Issues Packages Projects Releases Wiki Activity

ggml : sync latest changes from ggml and llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2023-04-13 18:53:44 +03:00
parent ebef1e8620
commit 2f889132c6
3 changed files with 188 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
ggml.h
View File

@@ -177,11 +177,12 @@ extern "C" {
#include <stddef.h>
#include <stdbool.h>
#define GGML_MAX_DIMS 4
#define GGML_MAX_NODES 4096
#define GGML_MAX_PARAMS 16
#define GGML_MAX_CONTEXTS 64
#define GGML_MAX_OPT 4
#define GGML_MAX_DIMS 4
#define GGML_MAX_NODES 4096
#define GGML_MAX_PARAMS 16
#define GGML_MAX_CONTEXTS 64
#define GGML_MAX_OPT 4
#define GGML_DEFAULT_N_THREADS 4
#ifdef __ARM_NEON
// we use the built-in 16-bit float type
@@ -198,13 +199,14 @@ struct ggml_object;
struct ggml_context;
enum ggml_type {
GGML_TYPE_Q4_0,
GGML_TYPE_Q4_1,
// explicitly numbered values are used in llama.cpp files
GGML_TYPE_F32 = 0,
GGML_TYPE_F16 = 1,
GGML_TYPE_Q4_0 = 2,
GGML_TYPE_Q4_1 = 3,
GGML_TYPE_I8,
GGML_TYPE_I16,
GGML_TYPE_I32,
GGML_TYPE_F16,
GGML_TYPE_F32,
GGML_TYPE_COUNT,
};