llama.cppProduct update
llama.cpp · v0.4.1
llama.cpp v0.4.1 adds support for Maple 20B-A1B, Tencent Hy 4 and Spark2.5, with Maple 20B-A1B on CPU only and Tencent Hy 4 as preview architecture support, improves JSON schema handling, chat parsing, logging and server child-process management, and updates ggml to v0.24.0. The deprecated --mmap, --mlock and --direct-io arguments are removed in favor of --load-mode, the server enables --reasoning-preserve by default, and an LRU hang on multiple requests for the same model is fixed.
Saved . A shortened excerpt from GitHub Releases; the original publisher retains authorship.