ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Capture CUDA logging output (#7298)

Browse source 
* logging: output capture in cuda module

* fix compile error

* fix: vsnprintf terminates with 0, string use not correct

* post review

* Update llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

* Update llama.cpp

Co-authored-by: slaren <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
fraxy-v 2024-05-19 01:44:42 +03:00 • committed by GitHub
parent 059031b8c4
commit f5bf761747
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 75 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -1697,6 +1697,8 @@ struct llama_state {
llama_state() {
#ifdef GGML_USE_METAL
ggml_backend_metal_log_set_callback(log_callback, log_callback_user_data);
#elif defined(GGML_USE_CUDA)
ggml_backend_cuda_log_set_callback(log_callback, log_callback_user_data);
#endif
}
@ -18174,6 +18176,8 @@ void llama_log_set(ggml_log_callback log_callback, void * user_data) {
g_state.log_callback_user_data = user_data;
#ifdef GGML_USE_METAL
ggml_backend_metal_log_set_callback(g_state.log_callback, g_state.log_callback_user_data);
#elif defined(GGML_USE_CUDA)
ggml_backend_cuda_log_set_callback(g_state.log_callback, g_state.log_callback_user_data);
#endif
}