… Our primary goal is to create AI capabilities that offer superior value for money.” He also said developing its own chips gives Alibaba “guaranteed supply of AI computing power,” which he said is necessary given “the unique circumstances currently facing the AI industry in China” – likely a referen… …
… The GPU giant needs that many chips because, while SRAM may be fast, the chips are neither capacious nor compute-dense. Each Groq 3 LPU is capable of 1.2 petaFLOPS of FP8 and contains 500 MB of on board memory. …
… Despite the hypemaxxed branding, the chip’s Arm Neoverse V3 cores won’t be running AI models themselves. That’s a job for GPUs or one of the growing number of high-end AI ASICs. Instead, Arm sees its first datacenter CPU powering AI agents. …
… MORE CONTEXT Arm rolls its own 136-core AGI CPU to chase AI hype train SoftBank to build massive AI datacenter on former US nuclear weapons site Nvidia powers further into the CPU market with new rack systems packing 256 Vera processors We tested Intel's new chips for cash-strapped hardcore PC user… …
… The company signalled its intention to roll out more custom inferencing chips in 2024, and in a post about its custom silicon, reveals it built its latest chips “in close partnership with Broadcom.” The post names the four previously unknown chips as models 300, 400, 450, and 500 in the Meta Traini… …
… MORE CONTEXT Nvidia's on-again off-again H200 sales in China are now on again Chips... in spaaaace – courtesy of Nvidia Nvidia powers further into the CPU market with new rack systems packing 256 Vera processors Nvidia slaps $20B Groq tech into massive new LPX racks to speed AI response time Any ti… …
… The Department of Commerce is said to be drafting rules that would require chipmakers to obtain government approval before exporting AI chips to any country, effectively giving Washington a stranglehold on AI compute supply. …
… Approaches like supervised fine tuning provided a way for customers to achieve performance closer to that of proprietary models while also imbuing them with their company's domain knowledge. Since then, open-weight models have made significant gains, Qiao explained. …
… Alongside the models, Nvidia is also rolling out training frameworks to help developers generate synthetic data and fine tune the models for their specific systems, and inference blueprints for implementing the models. …
Systems Nvidia's on-again off-again H200 sales in China are now on again Beijing appears to have eased its policy of pushing local GPUs GTC Nvidia has called on its supply chain partners to begin manufacturing its ageing H200 GPUs to meet demand for chips in China, CEO Jensen Huang said Tuesday. …