OpenAI Shows Jalapeño Benchmarks, Beats GB300 at 700 Watts
OpenAI's Jalapeño inference chip claims up to 1.9x the throughput per kilowatt of Nvidia's GB300, running at less than half the rated power.
Inference Chip News and Analysis
3 verified stories covering Inference Chip, product updates and industry developments.
Nvidia Denies Plan to Ship LPU Chips to China by Year-End
Nvidia rejected a report that it would ship LPU inference chips to Chinese customers before year end, but the commercial logic behind the idea remains intact.
Dell unveils Vera Rubin servers, slashing inference costs by 90%
Dell and NVIDIA announced the PowerEdge XE9812 server with Vera Rubin NVL72, cutting AI inference token costs to one-tenth of Blackwell.