From bca51b528820d28f54ea092fd4deaafc812f39d9 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Sun, 14 Jan 2024 10:49:50 +0200 Subject: [PATCH] sync : llama.cpp --- examples/common-ggml.cpp | 2 +- scripts/sync-llama.last | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/common-ggml.cpp b/examples/common-ggml.cpp index 06a0f37bc..0b9c2aa18 100644 --- 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 43c27f528..23adc26dc 100644 --- a/scripts/sync-llama.last +++ b/scripts/sync-llama.last @@ -1 +1 @@ -c71d608ce7a1584bf5072f197919dd24f3a6163f +5f5fe1bd608fa2ed42af97b5f2ea31be6625fc48