github ggml-org/llama.cpp b12118

latest release: b12119
pre-releaseone hour ago
Details

opencl: improve decode perf with FA (#31633)

  • opencl: use more workgroups for q4_K gate up + GLU

Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com

  • opencl: handle FA for GQA 2 and 6 with head size 256

Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com

  • opencl: handle FA for GQA 16 with head size of 128, 512

Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com

  • opencl: handle FA for GQA 2 with head size 512

Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com


Co-authored-by: Li He lih@qti.qualcomm.com

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.