Breaking speed limits left & right with #AI inference! Our high-speed support for @deepseek_ai R1 671B delivers 250 t/s per user, leaving other GPU-powered solutions in the dust Devs — get ready to turbocharge your AI with SambaNova Cloud More on our blog
AI HARDWARE
-
Untether AI Showcases Energy-Efficient AI Inferencing at ACC Detroit
By
–
Thanks #ACC Detroit for an amazing conference! @beach66's talk on "Energy-Efficient AI Inferencing for Automotive Computing" sparked great discussions on power optimization and real-world ADAS applications. Learn more about our #auto optimized solutions: untether.ai/markets/automoti…
→ View original post on X — @untetherai, 2025-04-02 19:04 UTC
-
SambaNova Cloud Enforces Rate Limits for Fastest Inference
By
–
Devs know rate limits make the world go 'round SambaNova Cloud enforces rate limits on inference requests per model to ensure that you're able to try the fastest inference! See below for details
-
Researcher Utilizing Shared Computing Infrastructure Resources
By
–
He’s camping on our research cluster
-
Company Frees Compute for Next Model Launch
By
–
We're freeing up compute for the launch of our next model
-
NVIDIA Blackwell Sets MLPerf Records with GB200 NVL72
By
–
In the latest #MLPerf Inference v5.0 round, the NVIDIA Blackwell platform set records — and marked NVIDIA’s first MLPerf submission using the GB200 NVL72 system, which delivered up to 30x more throughput on the Llama 3.1 405B benchmark.
-
Vision AI at Edge for Security and Surveillance Applications
By
–
We’re live at #ISCWest2025!
Stop by Booth #33051 @ Venetian Expo to see vision AI at the edge in action. Demos Kits Real-time analytics Axelera AI team ready to chat
Let’s talk AI for security, surveillance & more. https://
eu1.hubs.ly/H0h-xjW0 -
SambaNova Cloud: Building Full-Stack Apps with Advanced AI Accelerator
By
–
You heard it straight from @corbin_braun — SambaNova Cloud is for real 🔥
— SambaNova (@SambaNovaAI) 2 avril 2025
He gives an in-depth look at building a full-stack app with the fastest & most efficient #AI accelerator out there 🚀
Watch the full video 👇https://t.co/dCbnj79FHu#DeepSeekYou heard it straight from @corbin_braun — SambaNova Cloud is for real He gives an in-depth look at building a full-stack app with the fastest & most efficient #AI accelerator out there Watch the full video https://
youtube.com/watch?v=Eh0wIx
9nzsw
… #DeepSeek -
NXP Adopts MATLAB Simulink HDL Verifier IC Verification Workflow
By
–
NXP has adopted a new workflow using MATLAB, Simulink, and HDL Verifier for IC verification, improving edge case validation and control through constraints. More details here