From a5e160053641135557c10de66303187b5f0b02b8 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Thu, 14 Mar 2024 22:58:41 +0200 Subject: [PATCH] llama : fix integer overflow during quantization (#6063) --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index 10fd53469eb6f..2c384197492e8 100644 --- a/llama.cpp +++ b/llama.cpp @@ -11977,7 +11977,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n return new_type; } -static int32_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, const float * imatrix, std::vector & workers, const int nthread) { +static size_t llama_tensor_quantize_internal(enum ggml_type new_type, const float * f32_data, void * new_data, const int chunk_size, int nrows, int n_per_row, const float * imatrix, std::vector & workers, const int nthread) { std::mutex mutex; int counter = 0; size_t new_size = 0;