github ggml-org/llama.cpp b7927

latest releases: b7929, b7928, b7932...
3 hours ago
Details

sampling : delegate input allocation to the scheduler (#19266)

  • sampling : delegate input allocation to the scheduler

  • graph : compute backend samplers only if needed

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.