Open-weight & owned stack · Quantization efficiency

llama.cpp Adds LoRA Loading And Platform Builds

Sep 17, 2026, first seen via Training & inference tooling releases

llama.cpp b11019 fixes embedded GGUF and mmap handling, adds FILE*-based LoRA loading, and publishes broader platform builds.

Read the original at github.comOpens the publisher's site in a new tab

Also covering this

b11020github.com, Sep 17 b11018github.com, Sep 17

More in Open-weight & owned stack

Xiaomi Publishes MiMo-V2.6 Reinforcement Learning DashboardSep 17 Gemma Models Surpass One Billion DownloadsSep 16 llama.cpp Fixes Remote-Code-Execution VulnerabilitySep 16 Alibaba Releases Occamy Open-Weight AI AgentSep 15 Apple Enables Local Foundation Models On MacOSSep 15