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

YellowRoseCx · Jul 1, 2023 · 2f8cd97 · 2f8cd97
1 parent 471aab6
commit 2f8cd97
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 2 deletions.
diff --git a/ggml-metal.m b/ggml-metal.m
@@ -202,7 +202,9 @@ @implementation GGMLMetalClass
 
 void ggml_metal_free(struct ggml_metal_context * ctx) {
  fprintf(stderr, "%s: deallocating\n", __func__);
-
+ for (int i = 0; i < ctx->n_buffers; ++i) {
+ [ctx->buffers[i].metal release];
+ }
  free(ctx);
 }
 

diff --git a/llama.cpp b/llama.cpp
@@ -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;