← Companiesd-Matrix
Chips / supply chainUS· 11 items
Nvidia is opening its datacenter racks to rival inference-chip supplier d-Matrix, allowing competing accelerators to integrate into the same infrastructure ecosystem.▸ Nvidia's ecosystem move legitimizes multi-chip datacenters and validates alternative inference accelerators; reduces customer switching costs and signals confidence in heterogeneous compute architectures.
🕒 Sep 16, 04:06Source · Pluangimportance 69
AI inference chip startup d-Matrix, backed early by Samsung and SK, formally joins Nvidia's ecosystem.▸ Diversifies Nvidia's partner network in inference accelerators, legitimizing alternatives in the high-demand training-to-inference transition.
🕒 Sep 15, 16:35Source · finance.biggo.comimportance 65
AI inference chip startup d-Matrix announces a collaboration with NVIDIA amid rising demand for specialized inference accelerators.▸ NVIDIA's partnerships with inference-focused startups demonstrate the company's strategy to embed custom inference silicon across the ecosystem.
🕒 Sep 12, 22:18Source · TipRanksimportance 60
d-Matrix and NVIDIA plan an NVLink Fusion rack system for AI inference, backed by a multi-year product roadmap to standardize hardware deployments.▸ Standardized inference rack architectures will streamline GPU cloud deployments and improve hardware utilization rates for large-scale reasoning workloads.
🕒 Sep 11, 05:26Source · HPCwireimportance 85
Inference chip startup d-Matrix announced that its Raptor memory-based XPU will integrate with Nvidia's Rackscale Iron platform via Nvidia's NVLink Fusion interconnect for rack-scale AI inference.▸ Integration with Nvidia's ecosystem and platform demonstrates inference accelerator traction and offers customers an alternative to Nvidia's native H-series for specific inference workloads.
🕒 Sep 11, 01:06Source · Crypto Briefingimportance 70
d-Matrix will use NVIDIA's NVLink Fusion technology in its AI inference servers.▸ Inference chip startups integrating NVIDIA interconnect reduce differentiation and signal market consolidation around NVIDIA's hardware ecosystem.
🕒 Sep 11, 00:25Source · Financial-News.co.ukimportance 75
d-Matrix announced adoption of NVIDIA NVLink Fusion interconnect architecture to scale its next-generation Raptor XPU inference accelerator for rack-level deployments.▸ Inference-acceleration startup embracing NVIDIA ecosystem (NVLink Fusion + MGX rack standard) validates NVIDIA ecosystem lock-in; XPU deployment timing enables competitive inference alternative to H100 and H200.
◆ Official disclosure🕒 Sep 10, 23:00Source · NVIDIA Blogimportance 75
d-Matrix claims its new chip delivers 20x bandwidth density over NVIDIA Rubin.▸ Introduces a direct performance challenge to NVIDIA’s upcoming interconnect standards, potentially reshaping accelerator packaging economics.
🕒 Aug 25, 05:40Source · HotHardwareimportance 80
d-Matrix deployed Parasail Corsair heterogeneous AI inference accelerator, targeting cost-optimized inference for smaller models.▸ Inference ASIC vendor reaches production deployment; validates market segmentation where inference chips compete on TCO vs. GPU monolith.
🕒 Jul 12, 00:49Source · TipRanksimportance 58
Parasail is deploying d-Matrix Corsair inference accelerators alongside NVIDIA Hopper and Blackwell GPUs in a heterogene▸ PR Newswire press release — first-hand.
◆ Official disclosure🕒 Jul 08, 17:01Source · PR Newswire
d-Matrix, a Microsoft-backed semiconductor startup, has shipped its first AI chip to market.▸ New entrants with hyperscaler backing are diversifying the AI chip supply beyond Nvidia, creating competitive pressure and alternative architectures.
🕒 Nov 24, 23:00Source · insidermonkey.comimportance 65