10h ago

NVIDIA Plans HBF Integration With GPU-Direct Storage On Vera Rubin GPUs

——0——
Original post
OPZephyr#1497Zephyr@ZEPHYR_Z9

"NVIDIA is reportedly planning to implement GPU-Direct Storage (GIDS) with HBF on its next-gen Vera Rubin AI GPUs."

7:49 PM · May 23, 2026 View on X
QUOTE POSTZephyr#1497Zephyr@ZEPHYR_Z9

Yup, using HBF for GIDS doesn't even make sense HBF won't be used for any write-heavy tasks like KV cache storage (as it will kill the NAND in 2 years) You can use it for storing weights If it's ever adopted, the structure will be something like 8 HBM stacks + 4 HBF stacks

"NVIDIA is looking to use high-reliability, high-speed NAND, such as 200M IOPS NAND, for GIDS. It is not considering HBF."

JukanJukan@jukan05

The report claiming that NVIDIA is using HBF is fake news. I’m extremely disappointed in TrendForce. For a reputable firm like TrendForce to cite a The Elec article that was based on one professor’s opinion, and then reinterpret it as if The Elec reported that NVIDIA is trying to use HBF, is simply unacceptable. This is not true at all. NVIDIA is looking to use high-reliability, high-speed NAND, such as 200M IOPS NAND, for GIDS. It is not considering HBF.

3:37 AM · May 24, 2026 · 82.9K Views
5:00 AM · May 24, 2026 · 26.1K Views