Skip to content
Cut to the source.The real-time AI news wire.
Saved in a cookie.

Search tips

  • "exact phrase" the words together, in this order
  • -word leave out stories with the word
  • topic:robotics a topic by ID or name; quote names with spaces: topic:"open-weight models"
  • category:"AI agents" a category
  • company:openai a company, person, product or organization (also entity:)
  • source:forbes.com a publisher by site or name
  • type:analysis news, analysis, opinion, research paper and other kinds
  • after:2026-11-01 stories on or after that New York day; before:2026-11-10 on or before it
Subscribe
NewsletterAboutModels & ResearchAI AgentsAI DevelopmentInfrastructure & HardwareImage, Video & AudioRobotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society
Models & ResearchAI AgentsAI DevelopmentInfrastructure & HardwareImage, Video & AudioRobotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society
Robotics & Autonomous SystemsBusiness & IndustryPolicy & RegulationSafety & SecurityBenchmarks & EvaluationOpen Source & CommunityAI in Society

16 NovInfrastructure & Hardwaretensorjournal.com

vLLM 0.34.0 removes Model Runner V1 and makes MRV2 the only GPU runner

Off-white illustration of a cobalt track splitting into two lanes, where the upper mint lane is closed by a cobalt bar and a steady line of mint cubes flows along the lower lane into one large mint block.

AIAI-generated summary The vLLM project released version 0.34.0 on November 16, 2026, which removes Model Runner V1 and establishes MRV2 as the only GPU runner. The release notes state that version 0.34.0 adds support for Mistral Large 4 in FP8 and NVFP4 precisions.

Inference Optimization Model Serving

Read at tensorjournal.com

Share onXLinkedInBlueskyEmail

Latest stories

  • BNY Mellon & Microsoft Close First AI Treasury Trade

    20 November 2026

    nexchron.com — BNY Mellon and Microsoft AI agents autonomously negotiated a US Treasury bond price, the first AI-to-AI bond transaction, raising questions about speed, risk, and regulation.

  • Paper page - MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos

    20 November 2026

    Hugging Face — Join the discussion on this paper page

  • TokenEconomizer: Repository-specific learning, cost savings

    20 November 2026

    devotd.net — TokenEconomizer uses coding agent session histories to guide repository-specific instructions and tool adjustments. Microsoft Research reported lower…

  • Did AI-Driven Patching Cause the November Outages?

    20 November 2026

    explainx.ai — Congress heard AI sped up patching and strained legacy systems during November outages; not confirmed as one cyberattack.

  • AI Search Optimization: Chris M. Cartmill Says One Page, One Question Is the Formula That Earns AI Citations

    20 November 2026

    submitpr.org — AI Search Optimization: SEO specialist Chris M. Cartmill shares a simple formula for winning AI citations — one page, one customer question — and shows business…

TruncatedTruncated

Continuous coverage across AI research, agentic systems, infrastructure, and regulation.

Content

  • Latest
  • Archive
  • Topics
  • Newsletter
  • RSS Feed

About

  • About
  • Developers
  • Publishers
  • Advertise

Legal

  • Impressum
  • Privacy Policy
  • Terms & Conditions
  • Disclaimer
  • Contact

© 2026 Truncated. All rights reserved.

Truncated™ is a trademark of Three Things Media.