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

15 NovInfrastructure & Hardwareaipingnews.com

Baseten publishes DeepSeek engine, reports 2,060 tokens per second on eight B300s

AIAI-generated summary Baseten published an inference engine for the DeepSeek V4.1 Flash model, reporting a speed of 2,060 output tokens per second on eight Nvidia B300 GPUs. Teams with compatible hardware can run the DeepSeek weights on the engine, which was written in Rust and CUDA and released under the Elastic License 2.0.

NVIDIA DeepSeek DeepSeek CUDA GPUs

Earlier:
Lawyer upgrades eight-V100 private AI server to run 80% of…
+1 more earlier storiesCollapse earlier stories
  • Lawyer upgrades eight-V100 private AI server to run 80% of DeepSeek V4.1 Flash at 4-bit NVFP4 precision — adds 1TB of RAM, an Nvidia RTX 3090, and fixes crashes caused by a bad PSU
  • Lawyer builds private AI server with eight used Nvidia V100 GPUs — up to 215 tokens per second to keep legal files offline, costing about $2,400 per four-GPU board
Read at aipingnews.com

Share onXLinkedInBlueskyEmail

Latest stories

  • Europe needs ‘innovation-friendly’ regulation to catch up on AI, German official says

    19 November 2026

    Semafor — Marco-Alexander Breit said Europe needs to adjust its regulatory policy to halt a brain drain.

  • Copilot Home and Office go generally available with editing and coauthoring

    19 November 2026

    aipingnews.com — Copilot Home and Office integration became generally available on November 17.

  • Go from customer questions to completed transactions

    19 November 2026

    elevenlabs.io — Learn how to build an AI agent to handle customer booking conversations from start to finish with ElevenAgents

  • PixlStash 2.0: Image Library and LoRA Training in One Application

    19 November 2026

    mlllm.io — PixlStash 2.0 (v2.0.0 released November 10, 2026, v2.0.1 released November 16) is an open-source desktop application that groups faces by similarity...

  • Nvidia's October quarter revenues hit $115.8B, up 103%, with data center revenue up 110%

    19 November 2026

    gamesbeat.com — Nvidia reported revenues of $115.8 billion for the third fiscal quarter ended October 25, up 103% from a year ago.

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.