@jitllm.io
Java Inference Tornado toolkit | Powered by @tornadovm.org | jitllm.io
@stratika.bsky.socialReposted by @jitllm.ioYesterday my colleagues @maryxek.bsky.social and @mikepapadim.bsky.social showed live demos about using NVIDIA cuFFT and cuBLAS with @tornadovm.org for signal filtering and @jitllm.io!
NVIDIA performance is a jar away from Java.
@tornadovm.orgReposted by @jitllm.ioOptimized GPU libraries (e.g. cuBLAS, cuDNN, etc.) by NVIDIA, now one jar away for your Java - without caring about JNI.
We also show demos with Apache Flink and @jitllm.io.
Watch our talk in @devoxx.com 👇
youtu.be/6SPnBmQrYEk?...
@stratika.bsky.socialReposted by @jitllm.ioWe are at @devoxx.com, getting ready for our first hands-on #GPU lab for #Java!
We will be in BOF2 room at 16:50, with live demos!
@jitllm.ioThanks! We're currently working on extending TornadoVM's Metal capabilities for Apple silicon, and HIP support for AMD GPUs is next on our radar. Other suggestions are very welcome!
@jitllm.iojitLLM is part of the @langchain4j.dev 1.21.0 release! 🚀
Read more here: docs.langchain4j.dev/integrations...
@kotselidis.netReposted by @jitllm.ioOur latest addition to the TornadoVM family. Blazing fast AI inference at native speed!
@jitllm.ioCan Java compete with llama.cpp/ollama? YES! With @jitllm.io!
jitLLM uses NVIDIA CUDA features and libraries (cuBLAS, cuDNN) and reaches 0.90× to 1.12× of llama.cpp's throughput!
jitLLM is empowered by @tornadovm.org and will be soon in @langchain4j.dev and @quarkus.io.
@tornadovm.orgReposted by @jitllm.ioNext week we will be in @devoxx.com and speak about
@tornadovm.org, @jitllm.io and how we accelerate Java on GPUs, using #NVIDIA native libraries!
Come and talk to us, to learn more!
