sync : ggml (backend v2) (#3912)

* sync : ggml (backend v2) (wip)

* sync : migrate examples and llama.cpp to dynamic graphs (wip)

* sync : update tests + fix max op params to 64

ggml-ci

* sync : ggml-cuda

ggml-ci

* llama : fix save/load state context size

ggml-ci

* sync : try to fix build on tvOS

* sync : pass custom graph sizes in training examples

* sync : update graph copies to new ggml API

* sync : update sync-ggml.sh with new files

* scripts : fix header in sync script

* train : fix context size calculations

* llama : increase inference graph size up to 4096 nodes

* train : allocate grads for backward graphs

* train : allocate grads for gb_tmp

1 files changed, 6 insertions, 5 deletions

diff --git a/tests/test-opt.cpp b/tests/test-opt.cpp
index bb8af596..2c9997fc 100644
--- a/tests/test-opt.cpp
+++ b/tests/test-opt.cpp
@@ -109,10 +109,11 @@ int main(void) {
     struct ggml_tensor * d  = ggml_sub(ctx, c, ab);
     struct ggml_tensor * e  = ggml_sum(ctx, ggml_sqr(ctx, d));
 
-    struct ggml_cgraph ge = ggml_build_forward(e);
-    ggml_graph_reset(&ge);
+    struct ggml_cgraph * ge = ggml_new_graph_custom(ctx, GGML_DEFAULT_GRAPH_SIZE, true);
+    ggml_build_forward_expand(ge, e);
+    ggml_graph_reset(ge);
 
-    ggml_graph_compute_with_ctx(ctx, &ge, /*n_threads*/ 1);
+    ggml_graph_compute_with_ctx(ctx, ge, /*n_threads*/ 1);
 
     const float fe = ggml_get_f32_1d(e, 0);
     printf("%s: e = %.4f\n", __func__, fe);
@@ -121,9 +122,9 @@ int main(void) {
 
     ggml_opt(ctx, opt_params, e);
 
-    ggml_graph_reset(&ge);
+    ggml_graph_reset(ge);
 
-    ggml_graph_compute_with_ctx(ctx, &ge, /*n_threads*/ 1);
+    ggml_graph_compute_with_ctx(ctx, ge, /*n_threads*/ 1);
 
     const float fe_opt = ggml_get_f32_1d(e, 0);
     printf("%s: original  e = %.4f\n", __func__, fe);