AI Chips news and analysis on Web Pulse: 6900 curated articles tracking the latest AI Chips developments, tools, and research, updated continuously from vetted sources.
NVIDIA confirmed at IFA 2026 that RTX Spark Windows PCs from Lenovo and Acer will ship in October 2026, pairing a 20-core Grace CPU with a Blackwell-class RTX GPU, up to 128GB of unified memory, and up to 1 Petaflop of F…
A developer's technical breakdown of speculative decoding explains that single-batch LLM generation is memory-bandwidth bound rather than compute bound: on an Nvidia H100, a 70B FP16 model spends roughly 41.8 ms loading …
IBM's NorthPole brain-inspired chip is more than 20 times as fast and roughly 25 times as energy efficient as any microchip currently on the market for AI tasks, according to an IBM study led by Dharmendra Modha, IBM's c…
LLVM 23.1.0 was released on August 26, 2026, with almost 1300 patches contributed by Arm teams across architecture support, libraries, tools, performance and ML workloads. The release adds support for the Arm AGI CPU, Ar…
Google launched a refrigerator-sized satellite carrying four Tensor Processing Units (TPUs) aboard a SpaceX rocket on October 4, 2026, to test AI computing in orbit as part of its Project Suncatcher research initiative w…
A Systematization of Knowledge paper, "The KV Cache Is the New Memory Wall" (arXiv:2609.30854) by Tejinder Singh of Dell Technologies, unifies five families of KV cache reduction techniques — quantization, token eviction…
AI chips shipped through 2027 could run roughly 30–170 million concurrent frontier-model agents, supplying as many weekly working hours as about 140–720 million full-time employees, according to an analysis of high-bandw…
A scheduled inspection of a raised-floor plenum beneath a 2-megawatt AI cluster of 128 liquid-cooled racks, each holding eight NVIDIA H100 GPUs, uncovered zinc whiskers growing on galvanized floor supports. Once airflow …
Kazakh Prime Minister Olzhas Bektenov told the AI & Digital Bridge 2026 forum in Astana that Kazakhstan has the legal framework in place for large-scale artificial intelligence adoption, citing the country's Digital Code…
A user on the Level1Techs forum reported running four AMD Radeon R9700 GPUs on an AM4 platform to requantize a DeepSeek model to MXFP4 and run it in the vLLM engine, with the first layer of a 48-layer model taking 9m55s …
An engineer published a reference architecture for a sovereign, air-gapped AI stack for oil and gas health, safety and environment (HSE) work in Pakistan, sizing self-hosted models including GLM 5.3, Amazon Chronos-2, RF…
D-Matrix's Raptor accelerator, detailed in an ISCA 2026 paper, pairs a TSMC 4-nanometer logic die face-to-face with a custom DRAM die to reach up to 100 TB/s of bandwidth per card, with the paper reporting 4.71 times the…
DeepSeek open sourced its Huawei Ascend programming stack, according to AI Stock Wire. The release covers DeepSeek's software stack for Huawei's Ascend AI accelerators, a move that matters as an alternative to Nvidia's C…
Epoch AI reported that approximately 27.6 million H100-equivalent chips had been sold as of June 2026, a stock a September 2026 LessWrong assessment calculated could support between 24 million and 24 billion AI workers d…
The US Department of Justice arrested Greg Lui, 38, CEO of Earthmade Computer, on Thursday on charges of conspiring to violate the Export Control Reform Act and the Export Administration Regulations, plus federal smuggli…
Google has launched the first Project Suncatcher prototype satellite, built with satellite operator Planet and carried to orbit on SpaceX's Transporter-18 rideshare mission, and confirmed it has established contact and i…
A developer repacked Google's quantization-aware-trained Gemma 4 weights for vLLM and served them on a single Google Cloud TPU v5e chip, publishing the scripts and per-record results on GitHub. The int8 builds (w8a8) run…
Greg Lui, owner of California server provider Earthmade Computer, was arrested on October 1 after a federal grand jury returned a three-count indictment on September 29 alleging he helped route more than $300 million in …
CoreWeave put NVIDIA Vera Rubin NVL72 into production at its Fully Connected 2026 conference in San Francisco, with Cognition as the first customer running live workloads; Cognition engineers report up to 4.8x the total …
Qualcomm debuted the Snapdragon 8 Elite Extreme Gen 6 at its Snapdragon Summit 2026, bringing Adreno Neural Fusion AI graphics upscaling and frame generation to mainstream Android phones for the first time, while Arm unv…