Alfonso² Peterssen

run an LLM with a supercharged engine powered by Java and GraalVM (ht @alina-yurenko.bsky.social )

www.youtube.com/shorts/7zSEa...

16.04.2025 16:24 — 👍 17    🔁 3    💬 0    📌 0

✅ @graalvm.org Native Image
✅ Llama3.java
✅ Vector API, FFM API
✅ Apple Silicon ❤️

— `git clone github.com/mukel/llama3... `
— `sdk install java 25.ea.17-graal`
— `make native` (optionally preload a model for zero overhead)
— Profit!🚀

#Java #GraalVM #LLM #LLama

16.04.2025 12:13 — 👍 32    🔁 9    💬 0    📌 1

I had lots of fun talking about my early days as a dev, how I caused double credit bookings all over Germany, stopped smoking to survive long GraalVM meetings and how to heat the room with Java inception.

Already looking forward to part 2.

16.02.2025 14:38 — 👍 18    🔁 7    💬 1    📌 0

Crafting “Crafting Interpreters” – journal.stuffwithstuff.com

"Crafting Interpreters" checks all the boxes, here's a nice writeup from the author journal.stuffwithstuff.com/2020/04/05/c...

07.02.2025 15:44 — 👍 2    🔁 0    💬 0    📌 0

what's new in llama3.java and the upcoming @graalvm.org for JDK 24 🔥

Try it out here: github.com/mukel/llama3...
@stephanjanssen.be @mukel.bsky.social

#VDCERN #VoxxedDaysCERN

15.01.2025 10:24 — 👍 23    🔁 5    💬 1    📌 0

This will be a big deal 🪄🤩. Normally the debug experience of natively compiled languages get obfuscated due to compiler optimisations like inlining. Not here. All optimizations can be enabled to debug GraalVM native images and it looks just the same as without opts.

20.12.2024 12:00 — 👍 12    🔁 2    💬 1    📌 1

We just merged the current status of the upcoming JDWP support for @graalvm.org Native Image! 🥳

This will soon provide developers with the same debugging experience they are used to in Java, but for native images! Stay tuned for more details.

github.com/oracle/graal...

20.12.2024 11:46 — 👍 55    🔁 26    💬 3    📌 2

Excited to welcome @mukel.bsky.social as my co-speaker for the VoxxedDays #CERN talk on "The Era of AAP: Ai Augmented Programming using only Java" ☕️ 🚀 🔥
cern.voxxeddays.com/talk/the-era...

25.11.2024 14:12 — 👍 15    🔁 3    💬 0    📌 0

GitHub - mukel/llama3.java: Practical Llama 3 inference in Java Practical Llama 3 inference in Java. Contribute to mukel/llama3.java development by creating an account on GitHub.

https://buff.ly/40KmT0t
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.

16.11.2024 16:59 — 👍 28    🔁 13    💬 0    📌 2