sync : llama.cpp

diff --git a/examples/common-ggml.cpp b/examples/common-ggml.cpp
index 06a0f37bc47c0f7dfadc351370eccac6fa44b9c7..0b9c2aa18ad69a585631609eb65f819c0803a29e 100644 (file)
--- a/examples/common-ggml.cpp
+++ b/examples/common-ggml.cpp
@@ -184,7 +184,7 @@ bool ggml_common_quantize_0(
                 case GGML_TYPE_Q5_K:
                 case GGML_TYPE_Q6_K:
                     {
-                        cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements, hist_cur.data());
+                        cur_size = ggml_quantize_chunk((ggml_type) ttype, data_f32.data(), work.data(), 0, nelements/ne[0], ne[0], hist_cur.data(), nullptr);
                     } break;
                 case GGML_TYPE_F32:
                 case GGML_TYPE_F16:

diff --git a/scripts/sync-llama.last b/scripts/sync-llama.last
index 43c27f5289c3b76f665bbfb34f70dd969e31b307..23adc26dc6f1251748544195f4f6e1756c7a9c26 100644 (file)
--- a/scripts/sync-llama.last
+++ b/scripts/sync-llama.last
@@ -1 +1 @@
-c71d608ce7a1584bf5072f197919dd24f3a6163f
+5f5fe1bd608fa2ed42af97b5f2ea31be6625fc48