vLLM - Page 18
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
NVIDIA Releases Five Open Nemotron 3.5 Retrieval Models for AI Agents
NVIDIA's open Nemotron 3.5 Embed, Rerank and Parse models find, rank and extract evidence for AI agents. The benchmarks are NVIDIA's own.
NVIDIA’s Open Kumo Relational Model Predicts Straight From Databases
NVIDIA's open Kumo Relational model predicts churn, demand or fraud from databases with no training, and beats supervised ML on 41 tasks, NVIDIA says.
Node.js Fixes Four High-Severity Flaws, Including a Brotli Bug
Node.js 22.23.4, 24.22.1 and 26.12.1 fix four high-severity flaws, including a Brotli decoder bug the project says permits remote code execution.
Malicious LiteLLM Release on PyPI Stole Credentials, Researchers Say
LiteLLM 1.107.0 on PyPI carried a credential stealer and backdoor, SafeDep says. LiteLLM is treating it as SEV-0 and says to pin version 1.106.2.
Recursive Releases Flint, an Open-Weight Coding Model for Laptops
Recursive has released Flint, a 40B open-weight coding model that runs locally. It says AI built most of it; all benchmark and speed figures are its own.
UW and NVIDIA Release Open RFD4-Proteina Protein Design Model
UW's Institute for Protein Design and NVIDIA have released RFD4-Proteina, an open model they say is 5-10x better on benchmarks. No paper is cited yet.
IBM Says Granite Speech 5.0 2B Is Second-Best Open Model for English ASR
IBM has released Granite Speech 5.0 2B under Apache 2.0 for six-language transcription and translation, and refreshed two other speech models.
Krafton Releases Raon-1 Mini Preview, a 30B Open-Weight Model Built From Scratch
Krafton released a preview of Raon-1 mini, a 30B mixture-of-experts model under Apache 2.0, aimed at Korean. Benchmarks are its own; specs may change.
FastH3-Omni Cuts MiniMax H3 Video Generation Time Up to 11.9x, Its Makers Say
Nuva Lab and UC San Diego's FastVideo released FastH3-Omni, a distilled MiniMax H3 for reference-guided video with audio. Speed figures are the team's own.
Bria’s Fibo 2.0 Leads Open-Weights Image Editing, With Licence Limits
Bria's 8B Fibo 2.0 edits and generates images in one model and now tops Artificial Analysis's open-weights editing board. Commercial use needs a Bria deal.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
