[llama.cpp] Update llama.cpp to latest release b2581 (2024-03-30)

In order to get support for BERT based sentence embedding models like BAAI/bge-base-en-v1.5, mixedbread-ai/mxbai-embed-large-v1,  or others, update llama.cpp from

b1696 (2023-12-12):
https://github.com/ggerganov/llama.cpp/releases/tag/b1696

to the current latest release

b2581 (2024-03-30):
https://github.com/ggerganov/llama.cpp/releases/tag/b2581

BERT support was added to llama.cpp in February 2024:
ggml-org/llama.cpp#5423

Author: howlger

gradle.properties

@@ -1,3 +1,4 @@
+
 org.gradle.daemon=true
 org.gradle.jvmargs=-Xmx1024M --add-exports jdk.compiler/com.sun.tools.javac.api=ALL-UNNAMED \
   --add-exports jdk.compiler/com.sun.tools.javac.file=ALL-UNNAMED \
@@ -21,7 +22,7 @@ onnxruntime_version=1.17.1
 paddlepaddle_version=2.3.2
 sentencepiece_version=0.1.97
 tokenizers_version=0.15.0
-llamacpp_version=b1696
+llamacpp_version=b2581
 fasttext_version=0.9.2
 xgboost_version=2.0.3
 lightgbm_version=3.2.110