§ local-llm · storyline

Adds EXAONE 4.5 model support with vision and GQA

llama.cpp releases build b9451, removing unused Vulkan functions and shipping binaries across macOS, Linux, Windows, Android, and iOS platforms.

Jun 1 · 15:13:30 · primary fetch1 sourceupdated Jun 1 · 19:20:46

vulkan: Removed unused functions (#23175) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.2) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) DISABLED Android: Android arm64 (CPU) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.3 DLLs Windows x64 (Vulkan) Windows x64 (SYCL) DISABLED Windows x64 (HIP) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

read full article on github.com ↗

§ sources3 publications · timeline below

github.comllama.cpp b9451primary15:13:30
github.comllama.cpp b945519:20:46
github.comllama.cpp b945316:56:10

§ how this story moved

15:13:30primary — llama.cpp — Releases publishes the launch post.
16:56:10llama.cpp — Releases picks up coverage.
19:20:46llama.cpp — Releases picks up coverage.