{"slug": "kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache", "title": "Kioxia CM10: PCIe 6.0 SSD Aimed at Nvidia KV Cache", "summary": "Kioxia Corporation unveiled the CM10, a PCIe 6.0 SSD designed to offload Nvidia's KV cache for large-context LLM inference, targeting the Nvidia CMX architecture. The drive leverages PCIe 6.0's 64 GT/s per lane (double PCIe 5.0's 32 GT/s) and enterprise durability to serve as a low-latency cache tier between DRAM and conventional storage, addressing the memory bottleneck of long-context transformer models.", "body_md": "# Kioxia CM10: PCIe 6.0 SSD Aimed at Nvidia KV Cache\n\n## Why KV Cache Offload Changes the Storage Game\n\nKV 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.\n\nThat'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.\n\n## What the CM10 Actually Brings\n\nKioxia made some choices here that are worth noting:\n\n**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.\n\nI don't have the full datasheet in front of me, so I won't quote IOPS or latency numbers I can't verify. The interesting part is the positioning. Instead of selling raw capacity, Kioxia is selling a low-latency, high-bandwidth cache tier that sits between DRAM and conventional storage.\n\n## The Catch with PCIe 6.0 SSDs\n\nReal 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\n\n[Next Thomson Reuters' In-House AI Model Ranks Among the Best →](/en/news/4636/)", "url": "https://wpnews.pro/news/kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache", "canonical_source": "https://promptcube3.com/en/news/4638/", "published_at": "2026-08-01 07:15:32+00:00", "updated_at": "2026-08-01 07:24:03.113271+00:00", "lang": "en", "topics": ["ai-infrastructure"], "entities": ["Kioxia Corporation", "Nvidia", "CM10", "CMX"], "alternates": {"html": "https://wpnews.pro/news/kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache", "markdown": "https://wpnews.pro/news/kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache.md", "text": "https://wpnews.pro/news/kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache.txt", "jsonld": "https://wpnews.pro/news/kioxia-cm10-pcie-6-0-ssd-aimed-at-nvidia-kv-cache.jsonld"}}