Investigative report details how export-restricted Nvidia AI chips reach China — public records reveal how Chinese entities skirt US sanctions

The report also claims that some buyer institutions have ties to the CCP and the country’s defense and intelligence sectors. C4ADS says that it tracked 56 chips worth $1.7 million sold this way in the report’s July 2025 …

Investigative report details how export-restricted Nvidia AI chips reach China — public records reveal how Chinese entities skirt US sanctions

The report also claims that some buyer institutions have ties to the CCP and the country’s defense and intelligence sectors. C4ADS says that it tracked 56 chips worth $1.7 million sold this way in the report’s July 2025 …

Hot Chips 2026: Cerebras lays out the future of wafer-scale AI — Nexus system architecture triples rack-scale performance, CS-6 wafer to incorporate stacked DRA

Mounting the wafer-scale engines vertically in the backpack modules lets Cerebras do away with a PCB or substrate for the wafer to handle all its supporting infrastructure. Instead, the backpack connects the large copper…

Hot Chips 2026: Cerebras lays out the future of wafer-scale AI — Nexus system architecture triples rack-scale performance, CS-6 wafer to incorporate stacked DRA

Mounting the wafer-scale engines vertically in the backpack modules lets Cerebras do away with a PCB or substrate for the wafer to handle all its supporting infrastructure. Instead, the backpack connects the large copper…

Hot Chips 2026: Nvidia presents Groq 3 LPX architecture and unveils its first third-party inference benchmark — LP30-based rack already in production, company s

A Rubin GPU carries 288GB of HBM4 , roughly 576 times the memory of a single LP30, so a 31-billion-parameter model at FP8 needs on the order of 62 LPUs to hold its weights, and a large mixture-of-experts model runs into …

Hot Chips 2026: Cerebras lays out the future of wafer-scale AI — Nexus system architecture triples rack-scale performance, CS-6 wafer to incorporate stacked DRA

Mounting the wafer-scale engines vertically in the backpack modules lets Cerebras do away with a PCB or substrate for the wafer to handle all its supporting infrastructure. Instead, the backpack connects the large copper…