§ feed · storyline

llama.cpp b9037

llama.cpp releases build b9037, routing Hexagon M-tail row processing from HVX to HMX with loop unrolling optimisations across macOS, Linux, Android, Windows, and openEuler targets.

May 5 · 22:44:25 · primary fetch1 sourceupdated May 5 · 22:44:25

Hexagon: Process M-tail rows on HMX instead of HVX (#22724) hex-mm: process m-tail rows on HMX instead of HVX hmx-mm: unroll and optimize padded activation loop --------- Co-authored-by: Max Krasnyansky macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) 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) Ubuntu x64 (SYCL FP16) Android: Android arm64 (CPU) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.1 DLLs Windows x64 (Vulkan) Windows x64 (SYCL) Windows x64 (HIP) openEuler: openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph)

read full article on github.com ↗

§ sources1 publication · timeline below

github.comllama.cpp b9037primary22:44:25