beehive-lab/GPULlama3.java

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

54
/ 100
Established

Leverages TornadoVM's JIT compilation to automatically translate native Java tensor operations to OpenCL or NVIDIA PTX, supporting multiple model architectures (Llama3, Mistral, Qwen, Phi, Granite) in GGUF format. Integrates as an official model provider in LangChain4j and Quarkus, enabling GPU-accelerated inference within existing Java AI frameworks without additional glue code.

238 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

238

Forks

28

Language

Java

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/beehive-lab/GPULlama3.java"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.