Custom HBM drives 5x LLM inference speed boost

BenBajarin · x · 2026-09-01

SK Hynix (SKHY) claims up to a 5.15x improvement in LLM inference performance using Custom HBM. The company is also exploring a new type of memory called Compute-using DRAM, which would allow DRAM to perform certain computations directly inside the memory itself, reducing the need to move data back and forth between memory and the processor.

Original post →

More from Infra

Infra channel →