Google Research introduced TurboQuant, a quantization algorithm that compresses key-value cache to 3 bits without accuracy loss, achieving up to 8x performance increase over 32-bit unquantized keys on H100 GPUs.
Added to The Deploy Log , updated .
25 rows from Google Research in The Deploy Log are dated on or before this one, this one included.
It reached The Deploy Log 174 days after Google Research published it on .
The same day from Google Research: S2Vec (0 days apart). After it: Vibe Coding XR, 1 day later.
|
One line every time AI actually ships, as it ships, 24/7. Follow the wire: Threads | Bluesky
What this is
The Deploy Log is every deployment deployedbyai has carried, 2573 rows so far, each one sourced to the publisher's own page so you can check the number against it yourself.
All of it is free, with no signup: The Deploy Log, every edition, and the wire, one line every time AI actually ships, on Threads and Bluesky.