HomeTagsVLLM

vLLM - Page 21

Stories from vLLM come first, newest first, then stories from connected topics (Open Source, LLM, Hugging Face, AI Models, AI), each labelled with where it comes from. This view is not indexed by search engines.

Latest

Liquid AI Releases LFM2.5-24B-A2B, an Open-Weight Model for Running AI Agents on Your Own Device

Liquid AI's open-weight LFM2.5-24B-A2B has 24B parameters but uses only 2B at a time, built to run AI agents fast and privately on your own device.

AMD Launches Its Next Ryzen AI Halo Developer Platform, With Up to 192GB of Memory for Running Large AI Models Locally

AMD has launched its next Ryzen AI Halo developer platform, with the Ryzen AI Max+ PRO 495 and up to 192GB of memory for running big AI models locally.

Hundreds of Scientists, Including Geoffrey Hinton and Yoshua Bengio, Call for an International Body on AI Containment and Incident Reporting

Hundreds of scientists, including Geoffrey Hinton and Yoshua Bengio, call for an international body to set AI containment standards and log incidents.

LightOn Releases ColGrep-Agent-2B, an Open Local Code-Search Agent That It Says Cuts Claude Code’s Tokens by a Third

LightOn's open 2B-parameter ColGrep-Agent searches code locally for coding agents; it says Claude Code used 34% fewer API tokens than with grep.

Noiz AI and HKUST’s Helix World Adds Sound That Turns With the Camera

Noiz AI and HKUST release Helix World, a real-time world model that makes video and stereo sound together. All benchmarks are the authors' own.

Sperid Labs Releases Iris-3B, an Open Image Model That Skips the VAE

Sperid Labs released Iris-3B, a 3B image model with no VAE. Its paper finds no clear gain for depth or restoration. Code and weights are open.

LAION Releases Open Voice Converter Built on Resemble AI’s Chatterbox

LAION released an open voice-conversion model built on Chatterbox. The scores are LAION's own, and match to the target voice fell from 0.821 to 0.773.

How to Tell if an AI Answer Is Made Up: 5-Minute Checklist

Spot a made-up AI answer in 5 minutes: a numbered checklist covering sources, numbers, dates and cross-checks, plus what to do when you find a mistake.

Underdog’s Saluki 27B Shrinks Qwen3.8-27B to 7.89 GB, at a Maths Cost

Underdog's Saluki 27B is a 7.89 GB, 2-bit version of Qwen3.8-27B. Underdog says it passes more tool-calling tasks than the full model on its own 120-task test but scores 15 to 18% lower on competition maths. What quantisation means, and what the numbers do not prove.

Harness Buys Augment Code Assets, Plus TRL 1.15 and Genkit Dart 1.0

Four AI developer-tool updates from 8–9 October 2026: Harness buys selected Augment Code assets (not the whole company, price undisclosed), Hugging Face's TRL v1.15.0 claims up to 6.9× longer training sequences, Google's Genkit Dart reaches 1.0, and NVIDIA shows its Boro kernel-review tool. What each says, and what it doesn't.

Latest on TSN

Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.