haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

metal : disable graph concurrency optimization due to bug (#2413)

Browse source
This commit is contained in:
Georgi Gerganov 2023-07-27 11:00:54 +03:00
parent b5472ea0ad
commit 1a941869cb
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
llama.cpp
View file

@ -1722,9 +1722,10 @@ static bool llama_eval_internal(
#ifdef GGML_USE_METAL #ifdef GGML_USE_METAL
if (lctx.ctx_metal && N == 1) { if (lctx.ctx_metal && N == 1) {
if (!ggml_metal_if_optimized(lctx.ctx_metal)) { // TODO: disabled until #2413 is resolved
ggml_metal_graph_find_concurrency(lctx.ctx_metal, gf); //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_set_n_cb (lctx.ctx_metal, n_threads);
ggml_metal_graph_compute(lctx.ctx_metal, gf); ggml_metal_graph_compute(lctx.ctx_metal, gf);
ggml_metal_get_tensor (lctx.ctx_metal, cur); ggml_metal_get_tensor (lctx.ctx_metal, cur);