@dMatrix

Great to see our CEO Sid Sheth speaking at HumanX. “It’s not a money problem — it’s an architecture problem.” Scaling AI requires heterogeneous systems where specialized silicon works together to deliver real-time inference at scale. The Age of Inference is here. #AI #Inference #HumanX

Today at HumanX, d-Matrix CEO Sid Sheth will share why the GPU-only era is ending and what comes next for AI inference infrastructure. “The GPU-Only Era Is Over” April 9 | 2:25–2:40 PM Grove Theater humanx.co/speakers/sid-s… #HumanX #AIInference

“Inference is bigger than any one chip.” Thanks to @DCKnowledge and @ShaneSnider for the coverage of d-Matrix’s acquisition of GigaIO’s data center business and what it means for rack-scale AI inference infrastructure. Worth a read ↓

Excited to see GPU + Corsair systems running in the @gimletlabs environment. Heterogeneous AI infrastructure is how agentic workloads will run at scale. #AIInference #AgenticAI #AIInfrastructure

Today we announced the acquisition of GigaIO’s data center business, expanding d-Matrix’s rack-scale AI infrastructure capabilities. AI has entered the Age of Inference. Inference is now a systems problem — and we’re building what comes next. d-matrix.ai/announcements/… #AIInference #AIInfrastructure #AgeOfInference

We’re excited to be part of RISC-V Now! Join Satyam Srivastava, Distinguished Architect at d-Matrix, for “Solving Low-latency, Efficient Inferencing in the Datacenter.” Explore how next-gen AI accelerator architectures, powered by RISC-V, are delivering high performance, efficiency, and programmability for modern AI workloads. See you at RISC-V Now! on 4/21 at the DoubleTree Hotel in San Jose, CA. Registered: eventbrite.com/e/risc-v-now-b… #RISCV #RISCVNow

Agentic AI changed how we define success. Users don’t see your pipeline. They see one thing: did it work? New scoreboard: • Success rate • Quality • Latency • Cost per successful outcome That’s what matters in production. Read the blog: dmatrixstg.wpenginepowered.com/what-does-succ… #AI #Inference #AgenticAI

Big moment for AI inference 👇 Gimlet Labs’ $80M raise signals where things are going. Proud to partner on a multi-silicon approach built for real workloads: ⚡ Efficient for targeted inference ⚡ Built for production, not just training ⚡ Better performance per watt, lower cost The future isn’t one architecture. It’s the right mix. techcrunch.com/2026/03/23/sta… #AI #Inference #HeterogeneousComputing

If you’re at #RSAC this week, come see what we’re building. AI traffic is changing fast. Security needs to keep up. We’re demoing an LLM Network Firewall designed for real time, inline inspection not after the fact detection. Stop by Booth #N6181 or read the whitepaper. d-matrix.ai/pdf/LLM_Networ…

We’re heading to RSA next week. AI attacks aren’t batch problems anymore. They happen live. And most firewalls weren’t built for that. Inline, real-time AI firewall for LLM traffic. Come see it → Booth #N6181 #RSAC #CyberSecurity #AI

This week we brought together leaders across AI to talk about what comes next. Real-time AI isn’t the future. It’s happening now. The Age of Inference requires a new class of infrastructure. d-matrix.ai/announcements/… #AI #AIInference #RealTimeAI #AIInfrastructure

AI inference is no longer just a compute challenge. It is a memory challenge. At d-Matrix we built our architecture around SRAM for ultra-low latency inference. Now we’re pushing further with 3DIMC, a 3D stacked DRAM approach validated by our Pavehawk chip to scale memory for the next generation of AI workloads. Read the blog: d-matrix.ai/going-vertical… #AIInference #Semiconductors #AIInfrastructure #MemoryArchitecture #dMatrix

From AI startup to Series C, Sid Sheth and d-Matrix build specialized AI chips that makes AI fast and more sustainable. Learn how J.P. Morgan helps startups break into new markets. jpmorgan.com/growwithoutlim…

We recognized International Women’s Day with a panel discussion at d-Matrix focused on the realities women navigate in the workforce. From work life balance to career growth, it was an open and thoughtful conversation across the team. #InternationalWomensDay #WomenInTech #WomenInAI

All that empty space in data centers isn’t just dead weight. You can turn each of those open PCIe slots into token generation with next-generation accelerators designed to work with legacy hardware. Read more here: d-matrix.ai/using-whats-on…

Do we really need to put data centers in space? See what our founder and CEO @sidsheth has to say about this and more during an interview with @CNBCTV18Live'... and let us know what you think!

@CNBCTV18PrimeIN @sidsheth @Parikshitl Grateful for all the insightful conversation @Parikshitl had with our founder and CEO @sidsheth ...India CAN lead across the entire AI stack!

"The future of AI hinges on real-time, energy-efficient inference," says President & CEO of @dMatrix_AI, @sidsheth. Tells @Parikshitl, India can play across the full tech stack but must expand access to compute and energy.

Thank you @SharmaShradha & @YourStoryCo for spotlighting @SidSheth and d-Matrix. Training may dominate headlines. Inference will define the trillion-dollar AI economy. The Age of Inference requires purpose-built silicon. We’re building the infrastructure for what’s next. ⚡ 🔗 yourstory.com/2026/02/sid-sh… #AgeOfInference #AIInfrastructure #AIChips

There’s undeniable energy in India this week as the nation goes all in on AI. Day one at #IndiaAIImpactSummit was packed with panels, press, and important conversations between @sidsheth and the leaders shaping the country’s AI future. Thank you @Elets_TechnoMedia for hosting a standing-room-only opening panel alongside @GoI_MeitY, @IndiaAIMission, NxtGen, Govt of Jammu & Kashmir, and BWSSB. India is moving fast. We’re looking forward to supporting you on the journey. #AIInference #IndiaAI #SovereignAI