Kalsa
Engines / architectds / architectds/Strata

architectds/Strata

NVIDIAForkMIT

Speeds up prompt processing in Strata on NVIDIA GPUs. It is a fork of Niko1221/Strata.

Benchmarks

  • On RTX 5070 Ti alone with huihui Swift 1.5 (IQ3_XXS), it reads prompts at 298 tok/s, against 154 tok/s for stock 0.1.40.2 (+94%). Source Note: Derived from the stated 512-token prompt: 3.32 s to 1.72 s

Listing

Listed: Passed all seven checks.

Security review

Not reviewed yet.

Install

To install it, follow the project's own instructions on GitHub. The engine runs with your user's permissions. macOS doesn't sandbox it, so install only engines you trust.

Something wrong or out of date? Write to help@kalsa.io, or ask us to remove this page.