Infinity and HP double AI workload capacity on NVIDIA GB300 superchip
Infinity Artificial Intelligence Institute and HP Inc. announced that their joint effort using Infinity Auto Research optimized the NVIDIA Nemotron 3 Super model on the HP ZGX Fury workstation, which is powered by NVIDIA's GB300 Grace Blackwell Ultra Desktop Superchip. In tests the configuration handled roughly 2X concurrent AI requests and achieved about double the token throughput, all without…
Key points
- Infinity and HP achieved roughly 2X concurrent AI requests on HP ZGX Fury with NVIDIA GB300, without hardware changes
- Token throughput also doubled in the tested configuration
- Performance gain was delivered in under 24 hours of engineering work
HP’s Jim Nottingham said the result shows the ZGX Fury can deliver greater efficiency and support more simultaneous workloads, helping customers get more return from their AI investments. Infinity CEO Jeremy Nixon added that the performance gain was delivered in under 24 hours of engineering work and that the collaboration demonstrates how workload‑specific auto‑research optimization can extract the maximum from high‑performance chips.
Infinity and HP Deliver 2X Performance Gains on NVIDIA's GB300 Grace Blackwell Ultra Desktop Superchip
finance.yahoo.com · 20 October 2026
Loading the full article…
This text was published by finance.yahoo.com and written by Business Wire. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Hardware & Compute
All →- Intel and AMD collaborate on oneDNN optimizations for PyTorch · 1 src
- DeepSeek open-sources DeepInfer stack, potentially lowering inference costs · 5 src
- AMD adds FSR 4.1 support for RX 6000 GPUs, Xbox Series X/S and Ryzen AI chips · 1 src
- Google open-sources TorchTPU for native PyTorch on TPUs · 4 src
- xMEMS begins mass production of XMC-2400 and XMC-4800 micro‑cooling chips · 1 src
Comments
via GitHub Discussions