Kioxia CM10: PCIe 6.0 SSD Aimed at Nvidia KV Cache
The first PCIe 6.0 enterprise SSD that doesn't feel like a rubber-stamp announcement is Kioxia's CM10. While the industry has spent two years debating whether PCIe 6.0 is even necessary, Kioxia is already positioning this drive for something very concrete: Nvidia's CMX KV cache offload. That tells you more about where AI storage is heading than any roadmap slide.
Why KV Cache Offload Changes the Storage Game
KV cache is the memory bottleneck everyone hits when running long-context LLM inference. The transformer holds key-value tensors for every token, and with contexts stretching past 128K tokens, that state either fits in HBM or becomes a serious problem. Nvidia's CMX architecture seems designed to push that cache out of the GPU memory pool, which means the storage tier has to behave more like memory than a typical NVMe drive.
That's exactly where PCIe 6.0 matters. The protocol doubles bandwidth per lane compared to PCIe 5.0 — 64 GT/s instead of 32 GT/s. For an x4 link that's already significant, but for the CM10, the whole point is that you can feed a cache-hungry accelerator without making the I/O path the new bottleneck.
What the CM10 Actually Brings
Kioxia made some choices here that are worth noting:
- PCIe 6.0 interface with support for the new PAM4 signaling, which is a big leap over NRZ. It's not just marketing — it halves latency per unit of bandwidth.
- Enterprise durability tier, meaning it's built for sustained writes, not just benchmark reads. KV cache workloads are write-heavy during prompt processing and read-heavy during token generation.
- A form factor that likely fits standard E3.S or E1.S slots, so you don't need custom backplanes to test it.
- Targeting Nvidia CMX specifically, which is a strong signal that Kioxia sees this as an accelerator sidecar, not a general-purpose disk replacement.
The Catch with PCIe 6.0 SSDs
Real talk: PCIe 6.0 controllers are expensive, and the NAND to saturate even half of that bandwidth isn't cheap either. Most existing flash memory can do maybe 10–15 GB/s per device, while PCIe 6.0 x4 links can theoretically carry over 60 GB/s. So the CM10 is not about maxing out the interface — it's
All Replies (3)
This ignores the queue-depth behavior during inference. Does anyone have benchmarks showing the real-world impact of that bandwidth?
Latency consistency is the only thing that matters for NVMe-oF. Which specific setup are you using to measure this?
My KV cache misses plummeted after a week with the CM10. Anyone else seeing these gains?