github ggml-org/llama.cpp b7959

latest releases: b7964, b7962, b7961...
3 hours ago
Details

common : add common_speculative_is_compat() (#19270)

  • llama : add llama_memory_can_rm_suffix()

  • Revert "llama : add llama_memory_can_rm_suffix()"

This reverts commit d30e59b.

  • spec : check if the target context is compatible for spec decoding

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.