From 64234e3c4ea9c3cd2dd1a4f84c7da38e9607c747 Mon Sep 17 00:00:00 2001 From: Kawrakow Date: Fri, 17 Apr 2026 06:04:43 +0000 Subject: [PATCH] Fix compiler warning --- src/llama-load-tensors.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-load-tensors.cpp b/src/llama-load-tensors.cpp index a65e7f20..3e099a37 100644 --- a/src/llama-load-tensors.cpp +++ b/src/llama-load-tensors.cpp @@ -312,7 +312,7 @@ create_tensors_helper::create_tensors_helper(llama_model_loader & _ml, llama_mod // Split MTP layer's to graph if ((model.split_mode == LLAMA_SPLIT_MODE_GRAPH || model.split_mode == LLAMA_SPLIT_MODE_ATTN) && model.hparams.nextn_predict_layers > 0 && model.splits.size() > 1) { - int mtp_first = n_layer - model.hparams.nextn_predict_layers; + [[maybe_unused]] int mtp_first = n_layer - model.hparams.nextn_predict_layers; LLAMA_LOG_DEBUG("%s: MTP layer(s) %d-%d: split attention+FFN, nextn on per-device CUDA\n", __func__, mtp_first, n_layer - 1); }