From d8a0b870911f7e457cceb61c4764fd23673c4ea9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Fri, 31 May 2024 18:34:38 +0200
Subject: [PATCH] error if type_v != FP16 and not flash_attn

---
 llama.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/llama.cpp b/llama.cpp
index f67cb7e23..c48b79ecc 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -15866,6 +15866,11 @@ struct llama_context * llama_new_context_with_model(
         params.flash_attn = false;
     }
 
+    if (params.type_v != GGML_TYPE_F16 && !params.flash_attn) {
+        LLAMA_LOG_ERROR("%s: V cache quantization requires flash_attn\n", __func__);
+        return nullptr;
+    }
+
     llama_context * ctx = new llama_context(*model);
 
     const auto & hparams = model->hparams;