github ggml-org/llama.cpp b8021

2 hours ago
Details

opencl: add basic support for q4_1 (#19534)

  • opencl: add q4_1 mv

  • opencl: clean up

  • opencl: add flattened q4_1 mv

  • opencl: clean up

  • opencl: add basic q4_1 mm

  • opencl: fix whitespace

  • opencl: add general q4_0 mm

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.