From c8bc6e4ff4b9f1cb1e94eb56ddd10a95bd0108da Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Stanis=C5=82aw=20Szymczyk?= Date: Sat, 1 Feb 2025 12:43:14 +0100 Subject: [PATCH] llama : increased max_nodes as large MoE models use massive amounts of nodes during warmup --- src/llama-model.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 18bd0b071..c958edb87 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -3552,7 +3552,7 @@ size_t llama_model::size() const { } size_t llama_model::max_nodes() const { - return std::max(8192, tensors_by_name.size()*5); + return std::max(65536, tensors_by_name.size()*5); } size_t llama_model::n_devices() const {