From db1114955a967eda0481b246e83c70a9fc44bddd Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Mon, 2 Dec 2024 07:00:03 +0100
Subject: [PATCH] chunking by default.

---
 server/text_generation_server/models/globals.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/globals.py b/server/text_generation_server/models/globals.py
index dfae8ed2..8d988ad5 100644
--- a/server/text_generation_server/models/globals.py
+++ b/server/text_generation_server/models/globals.py
@@ -12,7 +12,7 @@ PREFIX_CACHING = os.environ["PREFIX_CACHING"].lower() in {
     "1",
     "true",
 }
-PREFILL_CHUNKING = os.getenv("PREFILL_CHUNKING", "0").lower() in {"1", "true"}
+PREFILL_CHUNKING = os.getenv("PREFILL_CHUNKING", "1").lower() in {"1", "true"}
 log_master(logger.info, f"Using prefix caching = {PREFIX_CACHING}")
 _expected = {"paged", "flashdecoding", "flashinfer"}
 assert (