AI Chips news and analysis on Web Pulse: 6909 curated articles tracking the latest AI Chips developments, tools, and research, updated continuously from vetted sources.
Huawei rotating chairman Wang Tao will present the company's upcoming Ascend 960 AI chips, slated for commercial availability in 2027, at Huawei's annual summit in Shanghai on Thursday. The unveiling advances Huawei's am…
Periodic Labs disclosed in a September 15th engineering post that its Neon 1-trillion-parameter model's final training run peaked at 1,300 Nvidia H200 GPUs, achieving over 95% cluster utilization, 4.1x the training throu…
At the AI Infra Summit, AMD argued that AI infrastructure should be designed around adaptability rather than any single chip or fabric, citing three auditable properties — adaptable, economical and open — as the way to p…
AMD reported leadership scores and expanded benchmark coverage in MLPerf Inference v6.1, whose results were released on September 16, 2026. AMD and its partners submitted validated results across dlrm-v3, llama2-70b, gpt…
AMD published a step-by-step recipe for reproducing its MLPerf Inference v6.1 submission results on AMD Instinct MI355X, MI350X, and MI350P GPUs, marking the company's fifth consecutive round of MLPerf Inference particip…
AMD published a step-by-step FlyDSL workflow for implementing a custom diffusion attention kernel, targeting vLLM's TiDAR (Think in Diffusion, Talk in Autoregression) mode with paged KV caches and scratch storage for spe…
EnCharge AI posted an on-site AI Software Engineer, Agent Harness role in Bengaluru, Karnataka, with remote-friendly options across India, seeking 10+ years of software engineering experience in backend systems or ML inf…
A RoboKrunch teardown compares NVIDIA's newly announced Jetson Orin Nano 2, which offers 78 TOPS but won't ship until H1 2027 at an unannounced price, against Orange Pi's Rockchip RK3588-based Orange Pi 5 Max, which deli…
Crusoe built a 300-megawatt gas turbine plant to supplement limited utility power at its Abilene, Texas data center campus, where grid delays forced the AI infrastructure firm to generate its own electricity, Chief Data …
VideoRouter launched as an OpenRouter-style routing service for video and image generation APIs, charging a flat 2% platform fee versus OpenRouter's 5%. The service negotiates volume pricing with GPU-hosting providers an…
Onsemi announced its Embedded Power Platform (EPP) at its investor day, a power-integration approach that embeds heterogeneous power dies into silicon and connects them through wafer-level redistribution layers instead o…
Apple is developing an enterprise AI server that would use two or four of its future M8 Ultra chips, with an expected release in 2029, according to The Information. The project reportedly received support from new Apple …
Nvidia unveiled its DSX platform at the AI Infra Summit, including DSX MaxLPS and the DSX Exchange API, to help datacenters squeeze more compute out of existing grid capacity. In testing with Lambda, Nvidia packed 19 nod…
Apple is developing enterprise AI servers powered by two or four M8 Ultra chips for 2029 and is considering integrating Nvidia's NVLink Fusion, according to The Information, while Bloomberg's Mark Gurman said Apple is al…
A developer benchmarked llama.cpp serving Google's Gemma 4 E2B Q4_0 GGUF on a single laptop, comparing CPU-only inference against the machine's 4 GB GTX 1650 Ti Max-Q, with the two arms differing only by the -ngl flag. T…
Axelera AI launched its Europa AI Processing Unit architecture, now available in three form factors and reaching up to 629 TOPS at a 45 W TDP. The Edge 232p single-chip card hits 83.4 tokens per second on Qwen 30B, while…
Apple is reportedly developing an enterprise AI inference server built around two or four of its own M8 Ultra chips, with a launch possible no earlier than 2029, according to The Information. Apple is considering Nvidia'…
Axis Communications, a professional security camera manufacturer with approximately 5,500 employees and about 90,000 system integration partners, is embedding AI analysis directly into its cameras via its ARTPEC system-o…
NVIDIA's Vera Rubin NVL72 delivered up to 3.7x higher throughput than the GB300 NVL72 on the Qwen3-VL model in MLPerf Inference v6.1 preview submissions, using vLLM with the NVIDIA Dynamo framework, while DeepSeek-R1 thr…
Epoch AI's AI Data Centers database now tracks 86 large AI facilities worldwide, covering an estimated 46% of all deployed AI compute as of June 2026, up from roughly 22% in early 2024. The tracked sites hold a combined …