diff --git a/go.mod b/go.mod
index 92836fd67c2d..00358507af47 100644
--- a/go.mod
+++ b/go.mod
@@ -9,7 +9,7 @@ require (
 	github.com/go-skynet/bloomz.cpp v0.0.0-20230529155654-1834e77b83fa
 	github.com/go-skynet/go-bert.cpp v0.0.0-20230716133540-6abe312cded1
 	github.com/go-skynet/go-ggml-transformers.cpp v0.0.0-20230714203132-ffb09d7dd71e
-	github.com/go-skynet/go-llama.cpp v0.0.0-20230929170139-79f95875ceb3
+	github.com/go-skynet/go-llama.cpp v0.0.0-20231003171153-6018c9d78c3a
 	github.com/gofiber/fiber/v2 v2.49.2
 	github.com/google/uuid v1.3.1
 	github.com/hashicorp/go-multierror v1.1.1
diff --git a/go.sum b/go.sum
index 39332916f1f9..84cb66e93b25 100644
--- a/go.sum
+++ b/go.sum
@@ -45,6 +45,8 @@ github.com/go-skynet/go-llama.cpp v0.0.0-20230923221031-d84f03c81a5e h1:ubROx+GE
 github.com/go-skynet/go-llama.cpp v0.0.0-20230923221031-d84f03c81a5e/go.mod h1:uejmv9IhRLb9FMhksGXgjAhvJpFnoTOX4+Dr9Lb0HSg=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230929170139-79f95875ceb3 h1:iFrK3lZyGCWGAde2XNxPKQUir8XUb43wVJghJFQQGXM=
 github.com/go-skynet/go-llama.cpp v0.0.0-20230929170139-79f95875ceb3/go.mod h1:uejmv9IhRLb9FMhksGXgjAhvJpFnoTOX4+Dr9Lb0HSg=
+github.com/go-skynet/go-llama.cpp v0.0.0-20231003171153-6018c9d78c3a h1:r0OXqNqtfBSQhUDODvM0TvwhWBplt/p6mCiZZ6MMYO0=
+github.com/go-skynet/go-llama.cpp v0.0.0-20231003171153-6018c9d78c3a/go.mod h1:uejmv9IhRLb9FMhksGXgjAhvJpFnoTOX4+Dr9Lb0HSg=
 github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 h1:tfuBGBXKqDEevZMzYi5KSi8KkcZtzBcTgAUUtapy0OI=
 github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572/go.mod h1:9Pwr4B2jHnOSGXyyzV8ROjYa2ojvAY6HCGYYfMoC3Ls=