.github/workflows/build.yml

@@ -23,7 +23,6 @@ on:
         "**/*.c",
         "**/*.cpp",
         "**/*.cu",
-        "ggml",
         "examples/server/frontend",
         "examples/server/frontend/**",
       ]
@@ -41,7 +40,6 @@ on:
         "**/*.c",
         "**/*.cpp",
         "**/*.cu",
-        "ggml",
         "examples/server/frontend",
         "examples/server/frontend/**",
       ]

ggml

@@ -1 +1 @@
-Subproject commit 8e800cef2948046cc47f9db6090491c6128ca42c
+Subproject commit 3f85508cddcba4e4a8a22414af379816f7945222

src/model/vae/vae.hpp

@@ -156,7 +156,7 @@ public:
             output = _compute(n_threads, input, false);
         }
 
-        runner_done();
+        free_compute_buffer();
 
         if (output.empty()) {
             LOG_ERROR("vae encode compute failed");
@@ -207,7 +207,7 @@ public:
             output = _compute(n_threads, input, true);
         }
 
-        runner_done();
+        free_compute_buffer();
 
         if (output.empty()) {
             LOG_ERROR("vae decode compute failed");