From c97ed60c3369294d5551ba099a88ddc509687df1 Mon Sep 17 00:00:00 2001
From: Gabe Goodhart <ghart@us.ibm.com>
Date: Thu, 19 Sep 2024 16:55:15 -0600
Subject: [PATCH] patch load progress
---
common/common.cpp | 2 ++
common/common.h | 7 +++++++
2 files changed, 9 insertions(+)
diff --git a/common/common.cpp b/common/common.cpp
index 8d0ed4f9..a09e8a53 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -955,6 +955,8 @@ 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 cb87c447..818a4a4a 100644
--- a/common/common.h
+++ b/common/common.h
@@ -266,6 +266,13 @@ struct gpt_params {
std::string mmproj = ""; // path to multimodal projector // NOLINT
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;
+
// embedding
bool embedding = false; // get only sentence embedding
int32_t embd_normalize = 2; // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm)
--
2.39.3 (Apple Git-146)
