Not

Hacker

News!

Not

Hacker

News!

AI-observed conversations & context

Daily AI-observed summaries, trends, and audience signals pulled from Hacker News so you can see the conversation before it hits your feed.

LiveBeta

Explore

Home
Hiring
Products
Companies
Discussion
Q&A
Privacy Policy

Resources

Visit Hacker News
HN API
Modal cronjobs
Meta Llama

Briefings

Inbox recaps on the loudest debates & under-the-radar launches.

Connect

Not affiliated with Hacker News or Y Combinator. We simply enrich the public API with analytics.

GPULlama3 | Not Hacker News!

Not

Hacker

News!

Home
Products
GPULlama3

Product Launch

anonymous

1 points

1 comments

Posted22 days agoActive20 days ago

GPULlama3

launchedlibrarydevelopers

Key Features

Llama model compiled to PTX/OpenCLIntegration with QuarkusGPU acceleration

Tech Stack

Java

Not

Hacker

News!

AI-observed conversations & context

Daily AI-observed summaries, trends, and audience signals pulled from Hacker News so you can see the conversation before it hits your feed.

LiveBeta

Explore

Home
Hiring
Products
Companies
Discussion
Q&A

PTX

OpenCL

Quarkus

Maven

GPU allocationjavaMachine Learningdevelopment_tools

Discussion (1 comments)

Showing 6 comments

lostmsu

22 days ago

1 reply

[delayed]

mikepapadim

22 days ago

1 reply

Yes, when you use the PTX backend it supports Tensor Cores.It has also implementation for flash attention. You can also write your own kernels, have a look here: https://github.com/beehive-lab/GPULlama3.java/blob/main/src/... https://github.com/beehive-lab/GPULlama3.java/blob/main/src/...

lostmsu

22 days ago

1 reply

[delayed]

mikepapadim

21 days ago

1 reply

https://github.com/beehive-lab/TornadoVM/pull/732 https://github.com/beehive-lab/TornadoVM/pull/313

lostmsu

20 days ago

[delayed]

mikepapadim