github ggml-org/llama.cpp b7248

4 hours ago

Warning

Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

server: fix duplicate HTTP headers in multiple models mode (#17698)

  • llama-server: fix duplicate HTTP headers in multiple models mode (#17693)

  • llama-server: address review feedback from ngxson

  • restrict scope of header after std::move
  • simplify header check (remove unordered_set)

macOS/iOS:

Linux:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.