Project
frozenfur
Translates an LLM into an optimized but frozen inference engine into FPGA or chip hardware for high speed, low power operation.
Translates an LLM into an optimized but frozen inference engine into FPGA or chip hardware for high speed, low power operation.
Highlights
Installation
Download a build below, or clone the source:
git clone https://github.com/Solifugus/frozenfur.gitDownloads & installation
Builds are coming soon. Grab the source from GitHub for now.