TGViewer
GitHub repos GitHub repos @github_repos · 27.5K subscribers
Post #13103 1.65K
tonbistudio/turboquant-pytorch
From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.
Language: Python
Stars: 586 Issues: 12 Forks: 78
https://github.com/tonbistudio/turboquant-pytorch
GitHub GitHub - tonbistudio/turboquant-pytorch: From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache… From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity. - tonbistudio/turboquant-pytorch
Open in Telegram All posts from @github_repos
More from @github_repos
  1. Oct 6, 2026ESPARGOS/esp-sdr ESP-SDR uses the undocumented raw I/Q capture functionality of ESP32 fami…
  2. Oct 5, 2026omlahore/RemoveMacAI Turn off Apple Intelligence on macOS 27 and get its disk space back.…
  3. Oct 5, 2026kargulstudio/sales-crm Language: TypeScript Stars: 1049 Issues: 1 Forks: 216 https://githu…
  4. Oct 5, 2026storytold/photocraft Language: Rust Stars: 1123 Issues: 34 Forks: 115 https://github.com/s…
  5. Oct 5, 2026fsiaonma/elpis elpis Language: TypeScript Stars: 544 Issues: 0 Forks: 4 https://github.com…
  6. Oct 4, 2026PSRben/VisionHOPE Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →