Post

Juan Fumero
@jfumero.dev

Thanks to @mukel.bsky.social for the llama2.java port and Roger Allen (github.com/rogerallen/l...) for the CUDA port, we were able to understand and shape TornadoVM for running LLMs and transformers architectures.

llama2.javallama2.java
Alina Yurenko@alina-yurenko.bsky.social

The University of Manchester team extended @mukel.bsky.social's Llama3.java (github.com/mukel/llama3...) with GPU support via the GraalVM JIT and TornadoVM: www.infoq.com/news/2025/06... Nicely done!👏

infoq.comGPULlama3.java Brings GPU-Accelerated LLM Inference to Pure Java

0 reposts1 like

No replies yet.