{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihhvd5f5h3ieezezmzrmup2zvxenylotvb3jr3z4hrq3rgsogc2z4",
    "uri": "at://did:plc:azwgjkqilqtufnhrpl2oxmkw/app.bsky.feed.post/3mfqfybe6tkz2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreifmwcfkqkwkthicxsnbzqqiwnu75gvdydx4gdhnoj3ggzegsq7slu"
    },
    "mimeType": "text/html; charset=utf-8",
    "size": 101674
  },
  "path": "/2026/02/sk-hynix-sandisk-hbf-ai-inference-memory/",
  "publishedAt": "2026-02-25T23:56:24.000Z",
  "site": "https://nerds.xyz",
  "tags": [
    "Artificial Intelligence",
    "AI inference",
    "AI infrastructure",
    "data center memory",
    "HBF memory",
    "HBM",
    "High Bandwidth Flash",
    "Open Compute Project",
    "Sandisk",
    "SK hynix",
    "SSD"
  ],
  "textContent": "\n\nSK hynix and Sandisk are working to standardize HBF memory under the Open Compute Project, positioning it as a new layer between HBM and SSDs for AI inference workloads. The companies say HBF can improve scalability, power efficiency, and total cost of ownership as AI shifts from training to large-scale deployment.",
  "title": "SK hynix and Sandisk want HBF to become the missing memory layer for AI inference"
}