From eb572f9ac64efa5087c823550127c3c3f3b4e1a8 Mon Sep 17 00:00:00 2001
From: Daniel Bevenius <daniel.bevenius@gmail.com>
Date: Fri, 5 Jul 2024 18:36:55 +0200
Subject: [PATCH] squash! llama : add early return for empty range

Remove the setting of cache.head to 0 when the range is empty.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
---
 src/llama.cpp | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/llama.cpp b/src/llama.cpp
index b2c302915..24356d2b4 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -3259,10 +3259,7 @@ static void llama_kv_cache_seq_add(
     if (p0 < 0) p0 = 0;
     if (p1 < 0) p1 = std::numeric_limits<llama_pos>::max();
     // If there is no range then return early to avoid looping over the cache.
-    if (p0 == p1) {
-        cache.head = 0;
-        return;
-    }
+    if (p0 == p1) return;
 
     if (cache.recurrent) {
         // for Mamba-like models, only the pos needs to be shifted