Inference & serving
Llamaj.cpp
Exposes llama.cpp capabilities to JVM applications through FFM bindings rather than a separate inference service.
Overview
Research summary
Llamaj.cpp connects Java and other JVM applications to the native llama.cpp inference engine through bindings generated with jextract and Java's Foreign Function and Memory API. Developers can load models, manage inference contexts, tokenize input, stream generated tokens and request embeddings from Java code. The project documents batching, sampling, speculative decoding and distributed inference capabilities backed by llama.cpp.
Its standard builds target macOS on Apple silicon and Linux x86_64; additional platforms and acceleration options require suitable native builds. The Java wrapper is Apache-2.0 licensed and distributes the corresponding MIT license for llama.cpp.
Repository summary
- Stars
- Unavailable
- Open issues
- Unavailable
- Last push
- Unavailable
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Version
- Unavailable
Recorded catalogue figures. View repository data and provenance →
Classification
Pricing & services
Paid services unknown
Whether the provider offers paid products or services has not been established.
Licence scope
The Java wrapper is Apache-2.0; the bundled llama.cpp component retains its MIT license.
Implementation
Recorded implementation details and interfaces for Llamaj.cpp.
Implementation details
Java FFM bindings generated with jextract around the native llama.cpp library.
- Languages
- Java
- Repository type
- source
Recorded interfaces and capabilities
Licence scope
The Java wrapper is Apache-2.0; the bundled llama.cpp component retains its MIT license.
Repository
Repository snapshots, release information and recorded maintenance signals.
Repository snapshot
- Stars
- Unavailable
- Open issues
- Unavailable
- Last push
- Unavailable
- Commits, 90 days
- Unavailable
- Repository activity
- Not scored
- Archived
- Not recorded
Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).
Maintenance and provenance
- Catalogue snapshot
- 2026-10-06
Documentation
Recorded references and research provenance for this entry.
Recorded sources 4
- https://github.com/gravitee-io/llamaj.cpp Project page · Linked repository · Research reference
- https://central.sonatype.com/artifact/io.gravitee.llama.cpp/llamaj.cpp Research reference
- https://github.com/gravitee-io/llamaj.cpp/blob/main/LICENSE.txt Research reference
- https://github.com/gravitee-io/llamaj.cpp/blob/main/licenses/LICENSE-llama-cpp Research reference
Research metadata
- Research date
- 2026-10-02
- Catalogue snapshot
- 2026-10-06
Community & social 1 channels
Communities
- ForumGravitee communityOfficialDiscussionSupport
Link details for Forum — Gravitee community
- Last checked