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

15
llama.h
View file

@ -62,12 +62,6 @@ extern "C" {
typedef int llama_token;
enum llama_log_level {
LLAMA_LOG_LEVEL_ERROR = 2,
LLAMA_LOG_LEVEL_WARN = 3,
LLAMA_LOG_LEVEL_INFO = 4
};
enum llama_vocab_type {
LLAMA_VOCAB_TYPE_SPM = 0, // SentencePiece
LLAMA_VOCAB_TYPE_BPE = 1, // Byte Pair Encoding
@ -151,13 +145,6 @@ extern "C" {
bool embedding; // embedding mode only
};
// Signature for logging events
// Note that text includes the new line character at the end for most events.
// If your logging mechanism cannot handle that, check if the last character is '\n' and strip it
// if it exists.
// It might not exist for progress report where '.' is output repeatedly.
typedef void (*llama_log_callback)(enum llama_log_level level, const char * text, void * user_data);
// model quantization parameters
typedef struct llama_model_quantize_params {
int nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
@ -526,7 +513,7 @@ extern "C" {
// Set callback for all future logging events.
// If this is not called, or NULL is supplied, everything is output on stderr.
LLAMA_API void llama_log_set(llama_log_callback log_callback, void * user_data);
LLAMA_API void llama_log_set(ggml_log_callback log_callback, void * user_data);
LLAMA_API void llama_dump_timing_info_yaml(FILE * stream, const struct llama_context * ctx);