AI Chips News
Latest AI Chips news and analysis — 170 articles tagged AI Chips on The Robotics Media.
- EdgeCortix unveils RAIDEN, a 3.36 PFLOPS Physical AI chiplet platform — — Tokyo-based EdgeCortix has launched RAIDEN, a modular chiplet-based Physical AI accelerator peaking at 3.36 PFLOPS of FP4 compute, 256 GB memory and 6...
- Q-CTRL clocks 12x speedup on IBM Quantum Nighthawk R2 with Fire Opal — — Q-CTRL's Fire Opal stack cut a 60-qubit fermionic simulation from 4 min 25 s on IBM Heron R3 to 23 s on Nighthawk R2 — a 12x speedup and more than 400...
- Siemens And TSMC Deepen AI Chip Design Pact, Add DRC Fixing Agent For N2 And A16 — — Siemens and TSMC extended their Open Innovation Platform tie-up on September 23, 2026 with a joint AI-powered DRC fixing agent and expanded Calibre, A...
- Discovered Materials Raises $9M Seed To Aim AI Agent Swarms At Cooler AI Chips — — YC-backed Discovered Materials pulled in $9M led by Lightspeed India to run swarms of AI research agents 24/7 in search of cooler substrate materials...
- BrainChip Puts Akida AKD1500 On A PCIe Card So Any Desktop Can Run Edge AI — — BrainChip drops its Akida AKD1500 neuromorphic silicon on a plug-and-play PCIe card, aiming to move edge-AI evaluation from lab benches to any worksta...
- PrismML Ports 1-Bit Bonsai LLM To Qualcomm Snapdragon Smart Glasses — — PrismML, an AI lab founded by Caltech researchers and advised by UC Berkeley's Ion Stoica, unveiled a Qualcomm Snapdragon AR1 Gen 1 build of its 2B-pa...
- TSMC Sets 3-6% Wafer Price Hike For 2027 As AI Orders Face 21% Bill — — TSMC has told customers wafer-out prices will rise 3-6% from January 2027, with an additional 10-15% HPC surcharge on AI overflow orders that could pu...
- IonQ to Install Superion 256 Quantum Computer at NVIDIA NVAQC — — IonQ's 256-qubit Superion system will become the first QPU inside NVIDIA's Accelerated Quantum Research Center, linked to a GB200 NVL72 supercomputer...
- Google Launches First TPU Satellites To Orbit On SpaceX Transporter-18 — — Google's Project Suncatcher will loft four Trillium TPUs aboard SpaceX's Transporter-18 rideshare on Oct 1, testing the case for orbital AI data cente...
- NVIDIA Ships Isaac ROS 5.0 With Agentic Workflows And 5.5x Faster Pose Tracking — — NVIDIA's Isaac ROS 5.0 adds AI-agent development skills, ROS 2 Lyrical and Ubuntu 24.04 support, and a FoundationPose library that estimates object po...
- D-Robotics Closes $400M Series C To Build The 'Brain For Every Robot' — — Hong Kong-based D-Robotics closed a $400 million Series C led by a global internet giant, funding a full-stack Sunrise chip and RDK developer platform...
- Qualcomm Unveils Snapdragon 8 Elite Gen 6 With 30B-Parameter On-Device AI — — At Snapdragon Summit 2026, Qualcomm launched the Snapdragon 8 Elite Gen 6 and a higher-binned Extreme variant, both on a 2nm node and tuned for on-dev...
- AMD Joins The $1 Trillion Club As Data-Center Revenue Doubles To $6.7B — — AMD crossed $1 trillion in market cap for the first time on September 21, 2026, driven by data-center revenue that more than doubled to $6.7B on AI-wo...
- FAA Launches SMART AI Air-Traffic Tool At Reagan, Dulles And BWI — — The FAA activated its $875M SMART AI air-traffic tool at Reagan National, Dulles and BWI on September 22, using 200 data streams to predict delays and...
- Morphotonics Closes €40M Series B To Scale Nanoimprint For AR Waveguides And Data Centers — — Dutch nanoimprint lithography leader Morphotonics closed a €40M Series B extension to scale AR-waveguide manufacturing and enter co-packaged optics fo...
- Alibaba Unveils Zhenwu V900 AI Chip, Targets 10-Trillion-Parameter Qwen — — At Apsara 2026, Alibaba unveiled the Zhenwu V900 AI chip and outlined Qwen models scaling to 5-10 trillion parameters, with a 20-GW data-center target...
- Microsoft Open-Sources TauGrid, A Kubernetes Stack For GPU AI Workloads — — Microsoft's Azure Kubernetes Service team has open-sourced TauGrid — an MIT-licensed, cloud-native stack that folds Kueue, KubeRay and GPU health moni...
- Apple Weighs M8 AI Server Return With Nvidia NVLink Fusion — — Apple is exploring an M8-powered AI server for enterprise customers built around Nvidia's NVLink Fusion, targeting a 2029 launch that would end its 18...
- MediaTek Debuts 2nm Dimensity 9600 Pro, Claims 61% Lower Multi-Core Power — — MediaTek's first 2nm SoC lands with a 2+3+3 all-big-core CPU, dual-NPU AI engine and 55% higher tokens-per-watt for on-device LLMs.
- Holtec Nuclear Pulls $900M IPO As AI Data-Center Trade Sours — — Holtec Nuclear has shelved its planned $900 million Nasdaq listing, days after nuclear equities cratered on fears the AI data-center compute boom is d...