llama.cpp ReleasesSource publicationSource language · English

[Pre-release / continuous build] b12291

Pre-release / continuous build: this is an experimental build, not a stable release.

Pre-release / continuous build: this is an experimental build, not a stable release.

vulkan: allow dequantized KV optimization with CM2 (#31526) * additional FA test cases Assisted-by: Codex * vulkan: allow dequantized KV optimization with CM2 Enable the KV dequantization optimization with coopmat2, guarded by a heuristic based on query tokens*GQA ratio. While doing this we saw very large speedups for certain head sizes, and it was because those head sizes were incorrectly treated as unaligned. So also fix those to be treated as aligned, which should help for when the dequant optimization doesn't apply. * gqa uses nbq2 for the stride, so we need to check that value for alignment * tests : use VARS_TO_STR18 for flash attention Assisted-by: Codex

Website: - https://llama.app

Attestations: - https://github.com/ggml-org/llama.cpp/attestations/66417308

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 24.04 s390x (CPU) - Ubuntu 26.04 s390x (CPU) - Ubuntu 26.04 s390x (zDNN) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (CUDA 12) - CUDA 12.8 libraries - Ubuntu x64 (CUDA 13) - CUDA 13.5 libraries - Ubuntu arm64 (CUDA 13) - CUDA 13.5 libraries - Ubuntu x64 (ROCm 10.0) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) - Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide

Android: - Android arm64 (CPU) - Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU) - setup guide

Windows: - Windows x64 (CPU) - Windows arm64 (CPU) - Windows arm64 (OpenCL Adreno) - Windows x64 (CUDA 12) - CUDA 12.4 DLLs - Windows x64 (CUDA 13) - CUDA 13.5 DLLs - Windows arm64 (CUDA 13) - CUDA 13.5 DLLs - Windows x64 (Vulkan) - Windows arm64 (Vulkan) - Windows x64 (OpenVINO) - Windows x64 (SYCL) - Windows x64 (ROCm 10.0)

openEuler: - DISABLED - openEuler x86 (310p) - openEuler x86 (910b, ACL Graph) - openEuler aarch64 (310p) - openEuler aarch64 (910b, ACL Graph)

UI: - UI

Original source

llama.cpp Releases

Content notes

Original publication and rights belong to the source.