Episode

TurboQuant: Google's 6x KV Cache Compression and the Quiet Economics of Long Context AI - June 14, 2026

Podcast
DX Today | No-Hype Podcast & News About AI & DX
Published
Jun 14, 2026
Duration seconds
767
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2207817/episodes/19342899-turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026.mp3
Audio
https://www.buzzsprout.com/2207817/episodes/19342899-turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026.mp3
JSON
/v1/public/podcasts/dx-today-no-hype-podcast-news-about-ai-dx-6434212/episodes/turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026
Markdown
/podcast/dx-today-no-hype-podcast-news-about-ai-dx-6434212/turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/dx-today-no-hype-podcast-news-about-ai-dx-6434212/episodes/turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/dx-today-no-hype-podcast-news-about-ai-dx-6434212/turboquant-google-s-6x-kv-cache-compression-and-the-quiet-economics-of-long-context-ai-june-14-2026.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Send us Fan Mail TurboQuant: Google's 6x KV Cache Compression and the Quiet Economics of Long Context AI Google Research's TurboQuant compresses the LLM key value cache to roughly three bits per coordinate with near zero accuracy loss, delivering at least six times less memory and up to eight times faster attention on NVIDIA H100 GPUs. We unpack how its two stage design pairs a training free random rotation with a one bit correction step, why a 70B model's 128K context cache shrinks from abo...