metal : concurrently dispatch commands (#2358)

* metal: concurrently dispatch commands

Function `ggml_metal_graph_find_concurrency` will run and write
commands that can be issued concurrently to metal context `concur_list`
array, when `ggml_metal_graph_compute` is called for the first time.

* metal: don't call find_concurrency automatically.

* metal : code style changes

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

1 files changed, 3 insertions, 0 deletions

diff --git a/llama.cpp b/llama.cpp
index b42b410..2d737bb 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -1720,6 +1720,9 @@ static bool llama_eval_internal(
 
 #ifdef GGML_USE_METAL
     if (lctx.ctx_metal && N == 1) {
+        if (!ggml_metal_if_optimized(lctx.ctx_metal)) {
+            ggml_metal_graph_find_concurrency(lctx.ctx_metal,&gf);
+        }
         ggml_metal_set_n_cb     (lctx.ctx_metal, n_threads);
         ggml_metal_graph_compute(lctx.ctx_metal, &gf);
         ggml_metal_get_tensor   (lctx.ctx_metal, cur);