Intel D-Series, Nvidia RTX PRO/GB202 moves, Gigabyte GB300 and Biren BR20X point to a fast-expanding enterprise accelerator market for on-prem inference.
Intel has turned Crescent Island into a commercial lineup: the D-Series. The D270 card combines 32 Xe3P cores, 256 XMX engines, up to 480 GB of LPDDR5X and 1.5 TB/s of bandwidth. Rated performance reaches 1.3 PetaFLOPS FP8, with support from FP4 to F...
Intel has announced the GPU D Series, the successor to products known as Crescent Island and aimed at enterprise inference. The announcement lacks VRAM or performance details, but the renaming signals a more direct positioning in the market for on-pr...
Intel has named its Crescent Island data center inference card D-Series and revealed D270 specs: 1.3 PFLOPS dense FP8 and 1.5 TB/s memory bandwidth. A signal for on-prem LLM serving economics.
Biren Technology is targeting the BR20X GPU for AI systems up to 1,024 chips, according to Yicai. US restrictions, however, are slowing mass production for the cloud. The analysis explains why this scale jump is not just a hardware challenge: it affe...
According to reports, Nvidia has suspended production of the GeForce RTX 5090 to focus capacity on AI data center and professional GPUs. The move signals a clear industrial priority: accelerated computing margins outweigh gaming margins. For self-hos...
According to an unconfirmed report, NVIDIA may stop the GeForce RTX 5090 and allocate GB202 chips to the RTX PRO series. If true, the shift would reshape the self-hosted GPU market, affecting high-VRAM options for local LLM inference and pushing team...
Gigabyte tested the W775-V10-L01 with NVIDIA GB300, recording more than 2.2 billion tokens per day on a Blackwell Ultra GPU, 800 Gbps from a ConnectX-8 SuperNIC, and a C2C link between Grace CPU and GPU. The deskside benchmark signals that high-capac...
