From 7b5264204f7aff4d72e6aee1f305e07ab1f5bd82 Mon Sep 17 00:00:00 2001
From: Georgi Gerganov <ggerganov@gmail.com>
Date: Fri, 2 Jan 2026 16:00:25 +0200
Subject: [PATCH] cont : fix

---
 src/llama-context.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index a5699dbec5..c2f34a475f 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -342,7 +342,7 @@ llama_context::llama_context(
 
         reserve();
 
-        if (cparams.flash_attn) {
+        if (!cparams.flash_attn) {
             if (ggml_is_quantized(params.type_v)) {
                 throw std::runtime_error("quantized V cache was requested, but this requires Flash Attention");
             }