Laser Focus World is an industry bedrock—first published in 1965 and still going strong. We publish original articles about cutting-edge advances in lasers, optics, photonics, sensors, and quantum technologies, as well as test and measurement, and the shift currently underway to usher in the photonic integrated circuits, optical interconnects, and copackaged electronics and photonics to deliver the speed and efficiency essential for data centers of the future.

Our 80,000 qualified print subscribers—and 130,000 12-month engaged online audience—trust us to dive in and provide original journalism you won’t find elsewhere covering key emerging areas such as laser-driven inertial confinement fusion, lasers in space, integrated photonics, chipscale lasers, LiDAR, metasurfaces, high-energy laser weaponry, photonic crystals, and quantum computing/sensors/communications. We cover the innovations driving these markets.

Laser Focus World is part of Endeavor Business Media, a division of EndeavorB2B.

Laser Focus World Membership

Never miss any articles, videos, podcasts, or webinars by signing up for membership access to Laser Focus World online. You can manage your preferences all in one place—and provide our editorial team with your valued feedback.

Magazine Subscription

Can you subscribe to receive our print issue for free? Yes, you sure can!

Newsletter Subscription

Laser Focus World newsletter subscription is free to qualified professionals:

The Daily Beam

Showcases the newest content from Laser Focus World, including photonics- and optics-based applications, components, research, and trends. (Daily)

Product Watch

The latest in products within the photonics industry. (9x per year)

Bio & Life Sciences Product Watch

The latest in products within the biophotonics industry. (4x per year)

Laser Processing Product Watch

The latest in products within the laser processing industry. (3x per year)

Get Published!

If you’d like to write an article for us, reach out with a short pitch to Sally Cole Johnson: [email protected]. We love to hear from you.

Photonics Hot List

Laser Focus World produces a video newscast that gives a peek into what’s happening in the world of photonics.

Following the Photons: A Photonics Podcast

Following the Photons: A Photonics Podcast dives deep into the fascinating world of photonics. Our weekly episodes feature interviews and discussions with industry and research experts, providing valuable perspectives on the issues, technologies, and trends shaping the photonics community.

Editorial Advisory Board

  • Professor Andrea M. Armani, University of Southern California
  • Ruti Ben-Shlomi, Ph.D., LightSolver
  • James Butler, Ph.D., Hamamatsu
  • Natalie Fardian-Melamed, Ph.D., Columbia University
  • Justin Sigley, Ph.D., AmeriCOM
  • Professor Birgit Stiller, Max Planck Institute for the Science of Light, and Leibniz University of Hannover
  • Professor Stephen Sweeney, University of Glasgow
  • Mohan Wang, Ph.D., University of Oxford
  • Professor Xuchen Wang, Harbin Engineering University
  • Professor Stefan Witte, Delft University of Technology

SambaNova Scorches NVIDIA in New Speed Test

Samba-1 Turbo performs at 1000 t/s, topping Artificial Analysis benchmark

SambaNova Systems, the generative AI solutions company with the fastest models and most advanced chips, is the clear winner of the latest large language model (LLM) benchmark by Artificial Analysis. Topping their Leaderboad at over 1000 tokens per second (t/s), Samba-1 Turbo sets a new record for Llama 3 8B performance.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20240529647645/en/

“SambaNova's Samba-1 Turbo has set a new record for large language model inference performance in recent benchmarking by Artificial Analysis." Micah Hill-Smith, Co-Founder & CEO of Artificial Analysis (Image source: Artificial Analysis)

“SambaNova's Samba-1 Turbo has set a new record for large language model inference performance in recent benchmarking by Artificial Analysis." Micah Hill-Smith, Co-Founder & CEO of Artificial Analysis (Image source: Artificial Analysis)

“Our mission is to give every enterprise a custom AI system that comes at a lower cost,” said Rodrigo Liang, CEO and founder of SambaNova. “Blazing inference speed that doesn’t compromise accuracy is what developers need to put the power of a personalized LLM into the hands of their organization to streamline workflows and innovate faster.”

Micah Hill-Smith, Co-Founder & CEO of Artificial Analysis stated: “SambaNova's Samba-1 Turbo has set a new record for large language model inference performance in recent benchmarking by Artificial Analysis.

Artificial Analysis has independently benchmarked Samba-1 Turbo performance on Meta’s Llama 3 Instruct (8B) at 1,084 output tokens per second, more than 8 times faster than the median output speed across providers we benchmark. Artificial Analysis has verified that Llama 3 Instruct (8B) on Samba-1 Turbo achieves quality scores in line with 16-bit precision.

New frontiers in language model inference speed unlock new ways of building AI applications. Emerging use-cases include agents taking multi-step actions while maintaining seamless conversation, real-time voice experiences and high-volume document interpretation.”

Unlike competitors, which run the same model on hundreds of chips, Samba-1 Turbo runs Llama 3 8B at 1000 tokens per second (t/s) on just 16 chips, and can concurrently host up to 1000 Llama3 checkpoints on a single 16-socket SN40L node. This is the fastest speed for serving Llama 3, while maintaining full precision, at a much lower cost than competitors. The nearest competitor requires hundreds of chips to run a single instance of each model due to memory capacity limitations, and GPUs offer lower total throughput and lower memory capacity. SambaNova can run hundreds of models on a single node while maintaining this record speed, providing a 10x lower total cost of ownership than competitors.

"Samba-1 Turbo’s speed shows the beauty of Dataflow, which streamlines data movement on SN40L chips, minimizing latency, and maximizing processing throughput. It’s superior to the GPU – the result is instant AI,” said Kunle Olukotun, co-founder of SambaNova Systems and renowned computer scientist at Stanford University.

Try Samba-1 Turbo today!

About SambaNova Systems

Customers turn to SambaNova to quickly deploy state-of-the-art AI capabilities to meet the demands of the AI-enabled world. Our purpose-built enterprise-scale AI platform is the technology backbone for the next generation of AI computing. We enable customers to unlock the valuable business insights trapped in their data. Our flagship offering, SambaNova Suite, overcomes the limitations of legacy technology to power the large complex foundation models that enable customers to discover new services and revenue streams, and boost operational efficiency.

Headquartered in Palo Alto, California, SambaNova Systems was founded in 2017 by industry luminaries, and hardware and software design experts from Sun/Oracle and Stanford University. Investors include SoftBank Vision Fund 2, funds and accounts managed by BlackRock, Intel Capital, GV, Walden International, Temasek, GIC, Redline Capital, Atlantic Bridge Ventures, Celesta, and several others. sambanova.aiinfo@sambanova.aiLinkedinX

Footnote: Artificial Analysis offers independent analysis of AI language models and API providers. The company provides benchmarking and related information to support people & organizations in choosing the right model for their use-case and which provider to use for that model.

Contacts

Stock Quote API & Stock News API supplied by www.cloudquote.io
Quotes delayed at least 20 minutes.
By accessing this page, you agree to the following
Privacy Policy and Terms Of Service.