github ggml-org/llama.cpp b12481

latest releases: b12483, b12482
pre-releaseone hour ago
Details

convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) (#32476)

  • convert : fix FP8 n-gram table export for qwen4exp

  • convert : dequantize block-scaled FP8 weight_scale_inv in ModelOpt checkpoints

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.