From d5a6e865f6d1377a6bbebcb8bb3091d202543ea9 Mon Sep 17 00:00:00 2001 From: Paul Tsochantaris Date: Thu, 8 Feb 2024 18:26:10 +0000 Subject: [PATCH] Whitespace --- llama.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/llama.cpp b/llama.cpp index b12543298..847c25b0c 100644 --- a/llama.cpp +++ b/llama.cpp @@ -7285,7 +7285,7 @@ static int llama_decode_internal( // TODO: this is mostly important for Apple Silicon where CBLAS is still performing very well // we still need some threads to process all non-mul_mat ops, but not too much to avoid interfering // with the BLAS calls. need a better solution - // MoE Special Case: This logic applies when hparams.n_expert == 0, i.e. the model is NOT an MoE model. When an MoE is + // MoE Special Case: This logic applies when hparams.n_expert == 0, i.e. the model is NOT an MoE model. When an MoE is // being processed then Accelerate/BLAS will not be involved, so capping would limit performance. if (n_tokens >= 32 && hparams.n_expert == 0 && ggml_cpu_has_blas() && !ggml_cpu_has_gpublas()) { n_threads = std::min(4, n_threads);