ggml : fix view init skipped after buft max_size split

ggml/src/ggml-alloc.c

@@ -1124,6 +1124,20 @@ static void free_buffers(ggml_backend_buffer_t ** buffers, const size_t * n_buff
     free(*buffers);
 }
 
+static bool alloc_ctx_tensors_finalize_views(struct ggml_context * ctx) {
+    for (struct ggml_tensor * t = ggml_get_first_tensor(ctx); t != NULL; t = ggml_get_next_tensor(ctx, t)) {
+        if (t->view_src != NULL && t->buffer == NULL) {
+            enum ggml_status status = ggml_backend_view_init(t);
+            if (status != GGML_STATUS_SUCCESS) {
+                GGML_LOG_ERROR("%s: failed to initialize view tensor %s\n", __func__, t->name);
+                return false;
+            }
+        }
+    }
+
+    return true;
+}
+
 static bool alloc_tensor_range(struct ggml_context * ctx,
         struct ggml_tensor * first, struct ggml_tensor * last,
         ggml_backend_buffer_type_t buft, size_t size,
@@ -1142,24 +1156,14 @@ static bool alloc_tensor_range(struct ggml_context * ctx,
     struct ggml_tallocr tallocr = ggml_tallocr_new(buffer);
 
     for (struct ggml_tensor * t = first; t != last; t = ggml_get_next_tensor(ctx, t)) {
-        enum ggml_status status = GGML_STATUS_SUCCESS;
-        if (t->data == NULL) {
-            if (t->view_src == NULL) {
-                status = ggml_tallocr_alloc(&tallocr, t);
-            } else if (t->buffer == NULL) {
-                status = ggml_backend_view_init(t);
-            }
-        } else {
-            if (t->view_src != NULL && t->buffer == NULL) {
-                // view of a pre-allocated tensor
-                status = ggml_backend_view_init(t);
+        if (t->view_src == NULL && t->data == NULL) {
+            enum ggml_status status = ggml_tallocr_alloc(&tallocr, t);
+            if (status != GGML_STATUS_SUCCESS) {
+                GGML_LOG_ERROR("%s: failed to allocate tensor %s\n", __func__, t->name);
+                free_buffers(buffers, n_buffers);
+                return false;
             }
         }
-        if (status != GGML_STATUS_SUCCESS) {
-            GGML_LOG_ERROR("%s: failed to initialize tensor %s\n", __func__, t->name);
-            free_buffers(buffers, n_buffers);
-            return false;
-        }
     }
 
     return true;
@@ -1217,6 +1221,11 @@ static ggml_backend_buffer_t ggml_backend_alloc_ctx_tensors_from_buft_impl(
         return NULL;
     }
 
+    if (!alloc_ctx_tensors_finalize_views(ctx)) {
+        free_buffers(&buffers, &n_buffers);
+        return NULL;
+    }
+
     ggml_backend_buffer_t buffer;
     if (n_buffers == 1) {
         buffer = buffers[0];

tests/test-alloc.cpp

@@ -583,6 +583,31 @@ static void test_reallocation() {
     }
 }
 
+// Parent nbytes > max_size leaves cur_buf_size > max_size. A following view
+// then triggers a split with this_size == 0, so the view-only residual range
+// skips alloc_tensor_range unless views are finalized after all splits.
+static void test_view_init_after_max_size_split() {
+    const size_t max_size = 16;
+    dummy_backend backend = dummy_backend_init(max_size);
+    auto [ctx, graph, ctx_ptr] = make_context();
+    (void) graph;
+
+    ggml_tensor * parent = make_input_with_size(ctx, 24); // 6 x f32, > max_size
+    ggml_tensor * view0  = ggml_view_1d(ctx, parent, 2, 0);
+    ggml_tensor * view1  = ggml_view_1d(ctx, parent, 2, 2 * sizeof(float));
+    assign_names(ctx);
+
+    ggml_backend_buffer_ptr buf(ggml_backend_alloc_ctx_tensors_from_buft(ctx, &backend.buffer_type));
+    GGML_ASSERT(buf);
+
+    for (ggml_tensor * t = ggml_get_first_tensor(ctx); t; t = ggml_get_next_tensor(ctx, t)) {
+        GGML_ASSERT(t->buffer != nullptr);
+        GGML_ASSERT(t->data != nullptr);
+    }
+    GGML_ASSERT(view0->view_src == parent);
+    GGML_ASSERT(view1->view_src == parent);
+}
+
 static void run(const char * name, void (*f)()) {
     printf("%s ", name);
     fflush(stdout);
@@ -604,5 +629,6 @@ int main() {
     run("test_multiple_buffer_types", test_multiple_buffer_types);
     run("test_buffer_size_zero", test_buffer_size_zero);
     run("test_reallocation", test_reallocation);
+    run("test_view_init_after_max_size_split", test_view_init_after_max_size_split);
     return 0;
 }