Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(cpp): progress_callback patch #99

Merged
merged 1 commit into from
Dec 20, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions cpp/common.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -1001,8 +1001,10 @@ struct llama_model_params common_model_params_to_llama(const common_params & par
mparams.kv_overrides = params.kv_overrides.data();
}

mparams.progress_callback = params.progress_callback;
mparams.progress_callback_user_data = params.progress_callback_user_data;
if (params.progress_callback != nullptr) {
mparams.progress_callback = params.progress_callback;
mparams.progress_callback_user_data = params.progress_callback_user_data;
}

return mparams;
}
Expand Down
4 changes: 2 additions & 2 deletions cpp/common.h
Original file line number Diff line number Diff line change
Expand Up @@ -282,8 +282,8 @@ struct common_params {
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data

llama_progress_callback progress_callback;
void * progress_callback_user_data;
llama_progress_callback progress_callback = nullptr;
void * progress_callback_user_data = nullptr;

std::string cache_type_k = "f16"; // KV cache data type for the K
std::string cache_type_v = "f16"; // KV cache data type for the V
Expand Down
19 changes: 11 additions & 8 deletions scripts/common.cpp.patch
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
--- common.cpp.orig 2024-11-21 11:03:19
+++ common.cpp 2024-11-21 11:03:20
--- common.cpp.orig 2024-12-20 13:06:22
+++ common.cpp 2024-12-20 13:05:42
@@ -4,10 +4,6 @@

#include "common.h"
Expand Down Expand Up @@ -42,20 +42,23 @@
mparams.rpc_servers = params.rpc_servers.c_str();
mparams.main_gpu = params.main_gpu;
mparams.split_mode = params.split_mode;
@@ -999,6 +1001,9 @@
@@ -999,6 +1001,11 @@
mparams.kv_overrides = params.kv_overrides.data();
}

+ mparams.progress_callback = params.progress_callback;
+ mparams.progress_callback_user_data = params.progress_callback_user_data;
+ if (params.progress_callback != nullptr) {
+ mparams.progress_callback = params.progress_callback;
+ mparams.progress_callback_user_data = params.progress_callback_user_data;
+ }
+
return mparams;
}

@@ -1124,220 +1129,6 @@
@@ -1123,221 +1130,7 @@

return false;
}

-
-static bool common_download_file(const std::string & url, const std::string & path, const std::string & hf_token) {
-
- // Initialize libcurl
Expand Down Expand Up @@ -95,7 +98,7 @@
- nlohmann::json metadata;
- std::string etag;
- std::string last_modified;
-

- if (file_exists) {
- // Try and read the JSON metadata file (note: stream autoclosed upon exiting this block).
- std::ifstream metadata_in(metadata_path);
Expand Down
8 changes: 4 additions & 4 deletions scripts/common.h.patch
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
--- common.h.orig 2024-11-21 10:21:53
+++ common.h 2024-11-21 10:23:00
--- common.h.orig 2024-12-20 13:06:22
+++ common.h 2024-12-20 13:05:53
@@ -41,6 +41,17 @@

struct common_control_vector_load_info;
Expand Down Expand Up @@ -30,8 +30,8 @@
bool warmup = true; // warmup run
bool check_tensors = false; // validate tensor data

+ llama_progress_callback progress_callback;
+ void * progress_callback_user_data;
+ llama_progress_callback progress_callback = nullptr;
+ void * progress_callback_user_data = nullptr;
+
std::string cache_type_k = "f16"; // KV cache data type for the K
std::string cache_type_v = "f16"; // KV cache data type for the V
Expand Down
Loading