dmowns on Nostr: RT @GoogleResearch: Introducing TurboQuant: Our new compression algorithm that ...
RT @GoogleResearch: Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delive…
Published at
2026-03-26 06:30:01 UTCEvent JSON
{
"id": "30762218dbdae4a1c1c1f74a31da5fb111a1fe0acf2c1d3eeaf8805994afa0a6",
"pubkey": "92868237e0dfb4cff36cf67f9ed667aaf8cc5a788c2207b8d99127cfeb35c978",
"created_at": 1774506601,
"kind": 1,
"tags": [
[
"r",
"https://twitter.com/toome123/status/2037053235568021683"
]
],
"content": "RT @GoogleResearch: Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delive…",
"sig": "edb8d688673a2dfb85973ec02cb2b85ebb313b03891f5345fdac9c7e92b397e50045365268bcc3d0511bd6eb189d4c87e28fc5dbe3a8d338546f5f1f235880b8"
}
