@dMatrix (@dMatrix_AI) header
@dMatrix (@dMatrix_AI) profile picture

Infinite Inference. No Latency.

Santa Clara, CA
Joined February 2022
Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)Photo by @dMatrix (@dMatrix_AI)
Today at #SC26, d-Matrix’s Satyam Srivastava presented a technical tutorial on programming Corsair. On Thursday, Satyam will join Zain Asgar of Gimlet Labs for a discussion on heterogeneous disaggregation. 🕜 Thursday, November 19 | 1:30PM CT 📍W185abc In the meantime, stop by Booth #4808 for live demos, conversations with the team, and fresh coffee! #AIInference #dMatrix
3
20
966
Watch an AI coding agent build an interactive browser app from one prompt, using speculative decoding powered by d-Matrix Corsair. See it live at #SC26 in Chicago, booth #4808.
26
4
43
954
Inference is heading to #SC26 next week. Visit d-Matrix at Booth #4808 for live demos and fresh coffee. And on Thursday, catch Satyam Srivastava on heterogeneous disaggregation for agentic AI workloads. 🕜 Nov. 19 | 1:30 PM CT 📍 W185abc #AIInference #dMatrix
2
2
12
629
Testing has to evolve with AI hardware. At ITC 2026, d-Matrix’s Adeeb Husnain and Pradip Thaker shared work from Corsair and Raptor on how new AI architectures are changing the way chips are tested. Thanks to Synopsys and the ITC Committee for bringing the community together. #Semiconductors #AIInference #dMatrix
9
588
Inference is a memory problem. d-Matrix CTO Sudeep Bhoja joins @semidoped to discuss data movement, in-memory compute, 3D-stacked DRAM, and what it means for the next generation of AI inference. Thanks to @vikramskr and the Semi Doped team for the conversation! Watch or listen to the full episode: semidoped.com/episodes/3d-st… #AIInference #Semiconductors #dMatrix
1
3
12
508
We’re honored to be nominated for the 2026 GSA Start-Up to Watch Award. Grateful to be recognized alongside other emerging semiconductor companies, and looking forward to the GSA Awards Celebration on Dec. 10 in Santa Clara. Learn more: gsaglobal.org/awards/2026/20… #GSA #GSAAwards26 #Semiconductors #dMatrix
1
1
12
556
AI inference is becoming the new scaling challenge. SquadRack is our reference blueprint for a rack-scale solution purpose-built for AI inference, using a disaggregated, standards-based approach designed to deploy in existing data centers. Read more: d-matrix.ai/scaling-ai-the-r… #AIInference #dMatrix
13
4
29
782
A little Halloween fun with the d-Matrix team. Great minds, creative spirits, and plenty of candy. Happy Halloween! 👻 #LifeAtdMatrix #Halloween
8
380
AI infrastructure needs to evolve to keep pace with inference demands. d-Matrix CEO @sidsheth joined @furrier and @NYSEWired & theCUBE during the CASPA CEO Summit for a discussion about accelerating AI inference through memory, scaling inference from cloud to the edge, and much more. Watch the full conversation: youtube.com/watch?v=jnzS9al0… #AIInference #Semiconductors #CASPA2026 #dMatrix
1
10
531
Proud to celebrate d-Matrix CEO @sidsheth as a recipient of Purdue University’s 2026 Outstanding Electrical and Computer Engineer Award. Congratulations to Sid and all of this year’s honorees, and thank you to the @PurdueECE community for the recognition. #PurdueECE #Semiconductors #AIInfrastructure #dMatrix
3
2
22
868
A great few days at the CASPA 35th Annual Conference & CEO Summit. d-Matrix CEO @sidsheth Sheth joined @KrishnaR_SiMa of @SiMa_Inc and Melton Chang of @SchneiderElec , moderated by @Srasgon of Bernstein, for a conversation on how the infrastructure stack is evolving for the next generation of AI. Thank you to the @CASPAorg team, and congratulations on an incredible 35 years! #CASPA2026 #AIInference #Semiconductors #dMatrix
11
544
From specialized processors to complete AI inference systems. d-Matrix is scaling up with Squadron™, a new Silicon Valley lab and a growing team. Silicon Valley Business Journal explores what’s next: bizjournals.com/sanjose/news… #AIInference
1
1
1
17
746
Tomorrow at #PyTorchCon, join d-Matrix Principal Engineer Tristan Webb for a Demo Theater session on how PyTorch can help accelerate kernel development for custom AI hardware. dmx-compressor: Accelerating the Development of Kernels for Custom ASIC Hardware 🕧 Wednesday, October 21 | 12:35 PM 📍 Community Expo, Concourse Level #PyTorchCon #AIInfrastructure #AIInference #dMatrix
7
460
Breaking through the memory wall. Rethinking AI inference. d-Matrix CEO @sidsheth joins Tae Kim (@firstadopter) to discuss memory-centric compute, 3D-stacked DRAM, and the future of low-latency AI inference. Read the interview: taekim.substack.com/p/an-int… #AIInference #AIInfrastructure
1
1
20
1,444