llama_cpp 0.3.0 → 0.3.2

data/ext/llama_cpp/src/ggml-cuda.h

@@ -8,10 +8,6 @@ extern "C" {
 
 #define GGML_CUDA_MAX_DEVICES       16
 
-struct ggml_tensor_extra_gpu {
-    void * data_device[GGML_CUDA_MAX_DEVICES]; // 1 pointer for each device for split tensors
-};
-
 void   ggml_init_cublas(void);
 void   ggml_cuda_set_tensor_split(const float * tensor_split);
 
@@ -29,6 +25,7 @@ void   ggml_cuda_transform_tensor(void * data, struct ggml_tensor * tensor);
 void   ggml_cuda_free_data(struct ggml_tensor * tensor);
 void   ggml_cuda_assign_buffers(struct ggml_tensor * tensor);
 void   ggml_cuda_assign_buffers_no_scratch(struct ggml_tensor * tensor);
+void   ggml_cuda_assign_buffers_force_inplace(struct ggml_tensor * tensor);
 void   ggml_cuda_set_main_device(int main_device);
 void   ggml_cuda_set_scratch_size(size_t scratch_size);
 void   ggml_cuda_free_scratch(void);

data/ext/llama_cpp/src/ggml-metal.m

@@ -202,7 +202,9 @@ struct ggml_metal_context * ggml_metal_init(void) {
 
 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);
 }