b37b496a12
This doesn't expose a UX yet, but wires the initial server portion of progress reporting during load
31 lines
1.4 KiB
Diff
31 lines
1.4 KiB
Diff
diff --git a/common/common.cpp b/common/common.cpp
|
|
index ba1ecf0e..cead57cc 100644
|
|
--- a/common/common.cpp
|
|
+++ b/common/common.cpp
|
|
@@ -1836,6 +1836,8 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params &
|
|
mparams.use_mmap = params.use_mmap;
|
|
mparams.use_mlock = params.use_mlock;
|
|
mparams.check_tensors = params.check_tensors;
|
|
+ mparams.progress_callback = params.progress_callback;
|
|
+ mparams.progress_callback_user_data = params.progress_callback_user_data;
|
|
if (params.kv_overrides.empty()) {
|
|
mparams.kv_overrides = NULL;
|
|
} else {
|
|
diff --git a/common/common.h b/common/common.h
|
|
index d80344f2..71e84834 100644
|
|
--- a/common/common.h
|
|
+++ b/common/common.h
|
|
@@ -174,6 +174,13 @@ struct gpt_params {
|
|
// multimodal models (see examples/llava)
|
|
std::string mmproj = ""; // path to multimodal projector
|
|
std::vector<std::string> image; // path to image file(s)
|
|
+
|
|
+ // Called with a progress value between 0.0 and 1.0. Pass NULL to disable.
|
|
+ // If the provided progress_callback returns true, model loading continues.
|
|
+ // If it returns false, model loading is immediately aborted.
|
|
+ llama_progress_callback progress_callback = NULL;
|
|
+ // context pointer passed to the progress callback
|
|
+ void * progress_callback_user_data;
|
|
};
|
|
|
|
void gpt_params_handle_model_default(gpt_params & params);
|