tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 13:05:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : release buffers when freeing metal context (#2062)

Browse Source
This commit is contained in:
Aaron Miller
2023-07-01 11:14:59 -07:00
committed by GitHub
parent 471aab6e4c
commit 2f8cd979ec
2 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
llama.cpp
View File

@ -253,7 +253,13 @@ struct llama_model {
struct llama_context {
llama_context(const llama_model & model, const llama_vocab & vocab) : model(model), vocab(vocab), t_load_us(model.t_load_us), t_start_us(model.t_start_us) {}
#ifdef GGML_USE_METAL
~llama_context() {
if (ctx_metal) {
ggml_metal_free(ctx_metal);
}
}
#endif
std::mt19937 rng;
bool has_evaluated_once = false;