HBF researchPreprintResearch
Catalog record / 12 Aug 2026
A full-stack study draws a sharp boundary around HBF
The study argues that HBF performs poorly as a drop-in SSD replacement for transient KV-cache traffic, while identifying selective, more read-oriented uses where it can remain valuable.
Why it matters
Its contribution is not simply a negative verdict: it separates workloads that align with NAND behavior from those that expose latency, granularity, and endurance limits.
Exact source title
HBF Sucks! A Full-Stack Characterization of High-Bandwidth Flash for LLM Inference
Tags
Reading rule
This record preserves the source's maturity label. A roadmap, research result, or announced specification should not be treated as independent evidence of shipping hardware.