diff --git a/misc/llama-cpp/Makefile b/misc/llama-cpp/Makefile
index a5e4b34a6e47..34e96d20604d 100644
--- a/misc/llama-cpp/Makefile
+++ b/misc/llama-cpp/Makefile
@@ -1,36 +1,36 @@
 PORTNAME=	llama-cpp
 DISTVERSIONPREFIX=	b
-DISTVERSION=	2517
+DISTVERSION=	2531
 CATEGORIES=	misc # machine-learning
 
 MAINTAINER=	yuri@FreeBSD.org
 COMMENT=	Facebook's LLaMA model in C/C++
 WWW=		https://github.com/ggerganov/llama.cpp
 
 LICENSE=	MIT
 LICENSE_FILE=	${WRKSRC}/LICENSE
 
 USES=		cmake:testing compiler:c++11-lang python:run shebangfix
 USE_LDCONFIG=	yes
 
 USE_GITHUB=	yes
 GH_ACCOUNT=	ggerganov
 GH_PROJECT=	llama.cpp
 GH_TUPLE=	nomic-ai:kompute:4565194:kompute/kompute
 
 SHEBANG_GLOB=	*.py
 
 CMAKE_ON=	BUILD_SHARED_LIBS
 CMAKE_OFF=	LLAMA_BUILD_TESTS
 CMAKE_TESTING_ON=	LLAMA_BUILD_TESTS
 
 LDFLAGS+=	-pthread
 
 OPTIONS_DEFINE=		EXAMPLES
 OPTIONS_SUB=		yes
 
 EXAMPLES_CMAKE_BOOL=	LLAMA_BUILD_EXAMPLES
 
 BINARY_ALIAS=	git=false
 
 .include <bsd.port.mk>
diff --git a/misc/llama-cpp/distinfo b/misc/llama-cpp/distinfo
index 5f9b2c05eba0..b1b023b87e9e 100644
--- a/misc/llama-cpp/distinfo
+++ b/misc/llama-cpp/distinfo
@@ -1,5 +1,5 @@
-TIMESTAMP = 1711342276
-SHA256 (ggerganov-llama.cpp-b2517_GH0.tar.gz) = 0b7b72b3602a6bd4092451b293cf3493dfc86fcb0cecafaccec8eb42ca72aef2
-SIZE (ggerganov-llama.cpp-b2517_GH0.tar.gz) = 8745201
+TIMESTAMP = 1711521264
+SHA256 (ggerganov-llama.cpp-b2531_GH0.tar.gz) = 8f746ae00f0728c8cef2c5f86e657de9599e7d235b3ed926696f6e3ed1162f62
+SIZE (ggerganov-llama.cpp-b2531_GH0.tar.gz) = 8752807
 SHA256 (nomic-ai-kompute-4565194_GH0.tar.gz) = 95b52d2f0514c5201c7838348a9c3c9e60902ea3c6c9aa862193a212150b2bfc
 SIZE (nomic-ai-kompute-4565194_GH0.tar.gz) = 13540496
diff --git a/misc/llama-cpp/pkg-plist b/misc/llama-cpp/pkg-plist
index 0cbb1e9993d3..bb040edf25a2 100644
--- a/misc/llama-cpp/pkg-plist
+++ b/misc/llama-cpp/pkg-plist
@@ -1,44 +1,45 @@
 %%EXAMPLES%%bin/baby-llama
 %%EXAMPLES%%bin/batched
 %%EXAMPLES%%bin/batched-bench
 %%EXAMPLES%%bin/beam-search
 %%EXAMPLES%%bin/benchmark
 %%EXAMPLES%%bin/convert-llama2c-to-ggml
 %%EXAMPLES%%bin/convert-lora-to-ggml.py
 %%EXAMPLES%%bin/convert.py
 %%EXAMPLES%%bin/embedding
 %%EXAMPLES%%bin/export-lora
 %%EXAMPLES%%bin/finetune
 %%EXAMPLES%%bin/gguf
 %%EXAMPLES%%bin/gguf-split
 %%EXAMPLES%%bin/gritlm
 %%EXAMPLES%%bin/imatrix
 %%EXAMPLES%%bin/infill
 %%EXAMPLES%%bin/llama-bench
 %%EXAMPLES%%bin/llava-cli
 %%EXAMPLES%%bin/lookahead
 %%EXAMPLES%%bin/lookup
 %%EXAMPLES%%bin/lookup-create
 %%EXAMPLES%%bin/lookup-merge
 %%EXAMPLES%%bin/lookup-stats
 %%EXAMPLES%%bin/main
 %%EXAMPLES%%bin/parallel
 %%EXAMPLES%%bin/passkey
 %%EXAMPLES%%bin/perplexity
 %%EXAMPLES%%bin/quantize
 %%EXAMPLES%%bin/quantize-stats
+%%EXAMPLES%%bin/retrieval
 %%EXAMPLES%%bin/save-load-state
 %%EXAMPLES%%bin/server
 %%EXAMPLES%%bin/simple
 %%EXAMPLES%%bin/speculative
 %%EXAMPLES%%bin/tokenize
 %%EXAMPLES%%bin/train-text-from-scratch
 include/ggml-alloc.h
 include/ggml-backend.h
 include/ggml.h
 include/llama.h
 lib/cmake/Llama/LlamaConfig.cmake
 lib/cmake/Llama/LlamaConfigVersion.cmake
 lib/libggml_shared.so
 lib/libllama.so
 %%EXAMPLES%%lib/libllava_shared.so