From 41318d708ed196ff727dce14d263a64b23c7333d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ma=C3=ABl=20Kerbiriou?= Date: Wed, 29 Mar 2023 18:10:07 +0200 Subject: [PATCH] llama : use the same threshold for OpenBLAS and ggml thread limiting (#577) --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index 2d0279258..aa0c362d9 100644 --- a/llama.cpp +++ b/llama.cpp @@ -856,7 +856,7 @@ static bool llama_eval_internal( // for big prompts, if BLAS is enabled, it is better to use only one thread // otherwise, the threads are spin-lock waiting for the BLAS calls and are degrading the performance ggml_cgraph gf = {}; - gf.n_threads = N > 255 && ggml_cpu_has_blas() ? 1 : n_threads; + gf.n_threads = N >= 32 && ggml_cpu_has_blas() ? 1 : n_threads; struct ggml_tensor * embd = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, N); memcpy(embd->data, tokens, N*ggml_element_size(embd));