github ggml-org/llama.cpp b10757

latest release: b10758
pre-release2 hours ago
Details

vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec (#27449)

  • vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec when NUM_COLS > 4. 5x perf at n=8

Assisted-by: Claude Opus 5

  • adds 2 cases per quant type at k=16*256 to the all_types mat-vec sweep

Co-authored-by: Marshall assistant@llama.cpp

Website:

Attestations:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.