A Java and JVM port of llama.cpp using jextract, enabling local large language model (LLM) inference through native foreign function and memory API interop. Natively supports macOS M-series and Linux x86_64 with GPU acceleration. Platform and hardware support (Windows, ARM, CUDA, etc.) can be extended through custom builds.

Latest Versions

61 versions โ†’
VersionVulnerabilitiesUsagesDate
1.1.x
1.1.1
0
May 06, 2026
1.1.0
1
Apr 17, 2026
1.0.x
1.0.3
1
Apr 09, 2026
1.0.2
0
Apr 07, 2026
1.0.1
0
Apr 03, 2026
0.10.x
0.10.7
0
Feb 15, 2026
0.10.6
0
Feb 05, 2026
0.10.5
0
Feb 02, 2026
0.9.x
0.9.0
0
Dec 10, 2025
0.8.x
0.8.15
0
Dec 09, 2025
0.8.14
0
Nov 24, 2025
0.8.13
0
Nov 17, 2025
0.7.x
0.7.6
0
Sep 23, 2025
0.7.5
0
Sep 22, 2025
0.7.4
0
Sep 19, 2025
0.6.x
0.6.1
0
Sep 10, 2025
0.6.0
0
Sep 09, 2025
0.5.x
0.5.2
0
Aug 29, 2025
0.5.1
0
Aug 29, 2025
0.5.0
0
Aug 25, 2025
0.4.x
0.4.13
0
Aug 15, 2025
0.4.12
0
Aug 08, 2025
0.4.11
0
Aug 07, 2025
0.3.x
0.3.3
0
Jun 24, 2025
0.3.2
0
Jun 22, 2025
0.3.1
0
Jun 20, 2025
61 versions โ†’