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

Add support for file load progress reporting callbacks (#434)

Browse source 
* File load progress reporting

* Move llama_progress_handler into llama_context_params

* Renames

* Use seekg to find file size instead

* More correct load progress

* Call progress callback more frequently

* Fix typo
This commit is contained in:
Jed Fox 2023-03-25 01:26:28 -04:00 • committed by GitHub
parent 36d07532ef
commit 58e6c9f36f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 39 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama.h
View file

@ -45,6 +45,8 @@ extern "C" {
} llama_token_data;
typedef void (*llama_progress_callback)(double progress, void *ctx);
struct llama_context_params {
int n_ctx; // text context
int n_parts; // -1 for default
@ -55,6 +57,11 @@ extern "C" {
bool vocab_only; // only load the vocabulary, no weights
bool use_mlock; // force system to keep model in RAM
bool embedding; // embedding mode only
// called with a progress value between 0 and 1, pass NULL to disable
llama_progress_callback progress_callback;
// context pointer passed to the progress callback
void * progress_callback_user_data;
};
LLAMA_API struct llama_context_params llama_context_default_params();