vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

metal : reusing llama.cpp logging (#3152)

Browse source 
* metal : reusing llama.cpp logging

* cmake : build fix

* metal : logging callback

* metal : logging va_args memory fix

* metal : minor cleanup

* metal : setting function like logging macro to capital letters

* llama.cpp : trailing whitespace fix

* ggml : log level enum used by llama

* Makefile : cleanup ggml-metal recipe

* ggml : ggml_log_callback typedef

* ggml : minor

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Rickard Hallerbäck 2023-09-27 17:48:33 +02:00 • committed by GitHub
parent 527e57cfd8
commit dc6897404e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 98 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

7
ggml.h
View file

@ -445,6 +445,12 @@ extern "C" {
GGML_OBJECT_WORK_BUFFER
};
enum ggml_log_level {
GGML_LOG_LEVEL_ERROR = 2,
GGML_LOG_LEVEL_WARN = 3,
GGML_LOG_LEVEL_INFO = 4
};
// ggml object
struct ggml_object {
size_t offs;
@ -1691,6 +1697,7 @@ extern "C" {
};
typedef void (*ggml_opt_callback)(void * data, float * sched);
typedef void (*ggml_log_callback)(enum ggml_log_level level, const char * text, void * user_data);
// optimization parameters
//