AI chip news

AI chip news from every vendor: Nvidia, AMD, Intel, Google TPU, AWS Trainium, custom accelerators and startups.

Dark navy cover reading "Google TPU 8i Max and TPU 8tx" with abstract square tiles labelled 8T, 8I, 8TX and 8I MAX, two tiles grouped for 8i Max
AI chip news ·

Google TPU 8i Max and TPU 8tx, announced November 9, 2026: what Google published

TPU 8i Max is two TPU 8i chips on one package; TPU 8tx pairs TPU 8t silicon with AMD EPYC hosts.

Typographic cover: "SambaNova SN50 in Supermicro racks" beside a grid of outlined squares labelled prefill, a dashed arrow, and a row of cyan bars labelled decode.
AI chip news ·

SambaNova SN50 heads to Supermicro inference racks on November 3, 2026

SambaNova SN50 specs, and Supermicro's November 3, 2026 plan for 10,000 SN50 chips paired with Nvidia GPUs.

Typographic cover: "AMD Helios racks running at Meta" beside an outlined rack of nine slots, the top three filled in cyan, labelled rack, test, deploy.
AI chip news ·

AMD Helios racks running at Meta, AMD says on October 27, 2026

AMD said on October 27, 2026 that its first Helios racks are installed and in testing at Meta, ahead of a wider rollout.

Typographic cover: "Vera Rubin on Google Cloud A5X" beside four outlined site blocks of GPU cells joined by dashed links, labelled 80K per site and 960K multi-site.
AI chip news ·

Google Cloud A5X with Vera Rubin NVL72 announced October 21, 2026

Google Cloud A5X instances on Vera Rubin NVL72, announced October 21, 2026, reach general availability next month.

Typographic cover: "vLLM and SGLang run natively on TPU" beside a stack diagram with vLLM and SGLang boxes above PyTorch and a solid TorchTPU layer.
AI chip news ·

vLLM and SGLang on TPU: Google's PyTorch engines, October 20, 2026

Google's new vLLM and SGLang engines run natively on TPU through TorchTPU, launched October 20, 2026.

Abstract network fabric linking three clusters of AI accelerators with blue, green and amber data lanes
AI chip news ·

Ultra Ethernet 1.1 adds scale-up links and collectives

Ultra Ethernet 1.1 adds a local accelerator profile, in-network collectives and new congestion controls.

Typographic cover: "Azure Maia 300: 96 accelerators in one rack" beside a grid of 96 outlined cells arranged as 24 rows of four, with a few highlighted in cyan.
AI chip news ·

Microsoft unveils Azure Maia 300 on October 12, 2026: 96-chip racks

Microsoft unveiled Azure Maia 300 on October 12, 2026: 288 GB of HBM4 per chip, 96 chips per 167 kW rack.

NVIDIA RTX Spark preorder headline on a dark grid with a teal circle and ring.
AI chip news ·

NVIDIA Opens RTX Spark Preorders for Windows AI PCs

Laptops are due October 16 and compact desktops in November; DGX Station for Windows remains a preview.

AI chip news ·

US eases AI chip export rule for the UAE on July 14, 2026: the changes

A US rule published on July 14, 2026 lets approved UAE entities receive advanced computing items without a license.

Typographic cover reading "Vera Rubin NVL72 in production" on a dark violet background with an abstract rising line
AI chip news ·

CoreWeave puts Vera Rubin NVL72 into production with Cognition

CoreWeave opened Vera Rubin NVL72 on September 30, 2026; Cognition is the first customer running production on it.

AI chip news ·

Huawei Ascend roadmap: 960, 970 and 980 dates set September 17, 2026

At Huawei Connect 2026 on September 17, Huawei set dates for the Ascend 960DT, 960PR, 970 and 980 AI chips.

AI chip news ·

Broadcom AI semiconductor revenue: $16.7 billion, reported Sep 2, 2026

Broadcom said on September 2, 2026 that AI semiconductor revenue reached $16.7 billion in its third fiscal quarter.

AI chip news ·

Nvidia Q2 fiscal 2027 data center revenue: $89.0 billion, Aug 26, 2026

Nvidia reported on August 26, 2026 data center revenue of $89.0 billion for the second quarter of fiscal 2027.

AI chip news ·

Nvidia Groq 3 LPX enters full production on August 24, 2026

Nvidia said on August 24, 2026 that its Groq 3 LPX inference accelerator is in full production, with Nebius first.

AI chip news ·

Cerebras unveils CS-4 on Aug 18, 2026: WSE-3T, three wafers per rack

Cerebras unveiled the CS-4 system on August 18, 2026, built on its WSE-3 Turbo wafer-scale processor.

Cover card reading "SK hynix begins HBM4 mass shipments", Chips, July 29, 2026, on a dark navy grid with a teal circle
AI chip news ·

SK hynix HBM4 mass production 2026: shipments began in Q2, Q4 ramp expected

SK hynix began HBM4 mass shipments in Q2 2026; its Q3 results expect HBM4 to be mainstream in Q4.

AI chip news ·

AMD launches Instinct MI400 Series on July 23, 2026: MI455X and MI430X

AMD launched the Instinct MI400 Series on July 23, 2026: the MI455X for frontier AI and the MI430X for HPC.

Coverage includes Microsoft Maia, Meta MTIA, custom chips from Broadcom and Marvell, Cerebras, Groq and Chinese AI chips, plus the supply chain (TSMC, HBM from SK hynix, Samsung and Micron, ASML) and export controls, from the companies’ own datasheets, releases and filings. Specs are compared in our AI chips table, rental prices in GPU prices, and background in our chip explainers.

The Model Press

What are you looking for?

Search by headline, topic or keyword.