Code

CUDA acceleration when using LoRAs#1970

Code

Merged

JohannesGaessler merged 1 commit intoggerganov:masterggerganov/llama.cpp:masterfrom JohannesGaessler:cuda-lora-fixJohannesGaessler/llama.cpp:cuda-lora-fixCopy head branch name to clipboardJun 28, 2023

+78-19

Commits

Commits on Jun 24, 2023

• CUDA GPU acceleration for LoRAs + f16 models

  JohannesGaessler

  committed
  afa8dd5

  Copy full SHA for afa8dd5