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

ggml: unify backend logging mechanism (#9709)

Browse source 
* Add scaffolding for ggml logging macros

* Metal backend now uses GGML logging

* Cuda backend now uses GGML logging

* Cann backend now uses GGML logging

* Add enum tag to parameters

* Use C memory allocation funcs

* Fix compile error

* Use GGML_LOG instead of GGML_PRINT

* Rename llama_state to llama_logger_state

* Prevent null format string

* Fix whitespace

* Remove log callbacks from ggml backends

* Remove cuda log statement
This commit is contained in:
bandoti 2024-10-03 12:39:03 -03:00 • committed by GitHub
parent e3c355ba65
commit d6fe7abf04
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
13 changed files with 197 additions and 340 deletions
Download patch file Download diff file Expand all files Collapse all files

15
ggml/src/ggml-impl.h
View file

@ -33,6 +33,21 @@ extern "C" {
#endif
#endif
//
// logging
//
GGML_ATTRIBUTE_FORMAT(2, 3)
void ggml_log_internal (enum ggml_log_level level, const char * format, ...);
void ggml_log_callback_default(enum ggml_log_level level, const char * text, void * user_data);
#define GGML_LOG(...) ggml_log_internal(GGML_LOG_LEVEL_NONE , __VA_ARGS__)
#define GGML_LOG_INFO(...) ggml_log_internal(GGML_LOG_LEVEL_INFO , __VA_ARGS__)
#define GGML_LOG_WARN(...) ggml_log_internal(GGML_LOG_LEVEL_WARN , __VA_ARGS__)
#define GGML_LOG_ERROR(...) ggml_log_internal(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
#define GGML_LOG_DEBUG(...) ggml_log_internal(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
#define GGML_LOG_CONT(...) ggml_log_internal(GGML_LOG_LEVEL_CONT , __VA_ARGS__)
// bitset
typedef uint32_t ggml_bitset_t;