Groqchat(chat.groq.com)

135 points by izzymiller 2 years ago | 83 comments

Writing a competitive BZip2 encoder in Ada from scratch in a few days (2024)(gautiersblog.blogspot.com)

100 points by etrez 1 year ago | 56 comments

Show HN: A Marble Madness-inspired WebGL game we built for Netlify(5-million-devs.netlify.com)

574 points by franck 1 year ago | 221 comments

An interactive Marble Madness-inspired WebGL browser game built with Three.js and Rapier physics to celebrate Netlify reaching 5 million developers.

Show HN: I made a Zero-config tool to visualize your code(staying.fun)

94 points by lezhu 1 year ago | 35 comments

Solitude as the antidote to misanthropy(christopherketcham.com)

41 points by well_i_never 2 years ago | 38 comments

Show HN: Game demo made with my homemade game engine(reprobate.site)

87 points by delduca 1 year ago | 48 comments

Running Qwen3.8 at 255 tok/s on a single 5090(meshapplied.com)

7 points by Ir0n 12 days ago | 0 comments

A page from meshapplied.com about running a Qwen LLM at 255 tokens per second on a single Nvidia RTX 5090 GPU; no page content was captured.

TornadoVM 7 Enables GPU-Native Workloads from Java Applications(infoq.com)

85 points by pjmlp 4 days ago | 17 comments

InfoQ news article on TornadoVM 7.3, an open-source framework for running Java code on GPUs, covering its FFM backend, CUDA library integration, multi-GPU support and jitLLM.

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac(github.com)

845 points by gitpusher42 2 months ago | 300 comments

GitHub repo for TurboFieldfare, a Swift/Metal inference engine running 4-bit Gemma 4 26B-A4B on M-series Macs in about 2 GB RAM by streaming experts from SSD.

Quickemu: Quickly run optimised Windows, macOS and Linux virtual machines(github.com)

411 points by overbytecode 2 years ago | 128 comments

GitHub repository for Quickemu, a tool that quickly creates and runs optimised Windows, macOS and Linux desktop virtual machines using QEMU.

Beating Google's kernelCTF PoW using AVX512(anemato.de)

320 points by anematode 1 year ago | 92 comments

Blog post describing how the author used AVX512IFMA to speed up Google's kernelCTF proof-of-work and win a $51k exploit submission race.

Grok3 Launch [video](x.com)

547 points by travelhead 1 year ago | 1157 comments

An X post from xAI containing a video of the Grok 3 model launch livestream.