github ggml-org/llama.cpp b7709

latest releases: b10229, b10228, b10227...
6 months ago
Details

vulkan: Disable large coopmat matmul configuration on proprietary AMD driver (#18763)

  • vulkan: Disable large coopmat matmul configuration on proprietary AMD driver

  • Also disable the large tile size

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.