From 502812b2b16c0f8388e0741424f23f45426eeda6 Mon Sep 17 00:00:00 2001
From: Colin Kealty <3266127+bartowski1182@users.noreply.github.com>
Date: Wed, 2 Apr 2025 22:52:13 -0400
Subject: [PATCH] Remove debug assert

---
 src/llama-quant.cpp | 2 --
 1 file changed, 2 deletions(-)

diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp
index 3e56b2b86c..e108a82f37 100644
--- a/src/llama-quant.cpp
+++ b/src/llama-quant.cpp
@@ -865,8 +865,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
         is_clip_model |= name.rfind("mm.", 0) == 0; // check the "mm." prefix
     }
 
-    GGML_ASSERT(qs.n_ffn_down_exp != 0);
-
     qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)model.hparams.n_layer;
 
     // sanity checks for models that have attention layers