Download Latest Version llama-b7823-bin-910b-openEuler-x86-aclgraph.tar.gz (59.5 MB)
Email in envelope

Get an email when there's a new version of llama.cpp

Home / b7820
Name Modified Size InfoDownloads / Week
Parent folder
llama-b7820-xcframework.zip < 18 hours ago 173.8 MB
llama-b7820-bin-win-vulkan-x64.zip < 18 hours ago 46.6 MB
llama-b7820-bin-win-sycl-x64.zip < 18 hours ago 119.6 MB
llama-b7820-bin-win-opencl-adreno-arm64.zip < 18 hours ago 24.6 MB
llama-b7820-bin-win-hip-radeon-x64.zip < 18 hours ago 361.1 MB
llama-b7820-bin-win-cuda-13.1-x64.zip < 18 hours ago 144.6 MB
llama-b7820-bin-win-cuda-12.4-x64.zip < 18 hours ago 219.4 MB
llama-b7820-bin-win-cpu-x64.zip < 18 hours ago 30.1 MB
llama-b7820-bin-win-cpu-arm64.zip < 18 hours ago 23.7 MB
llama-b7820-bin-ubuntu-x64.tar.gz < 18 hours ago 23.7 MB
llama-b7820-bin-ubuntu-vulkan-x64.tar.gz < 18 hours ago 40.5 MB
llama-b7820-bin-ubuntu-s390x.tar.gz < 18 hours ago 24.5 MB
llama-b7820-bin-macos-x64.tar.gz < 18 hours ago 83.2 MB
llama-b7820-bin-macos-arm64.tar.gz < 18 hours ago 29.5 MB
llama-b7820-bin-910b-openEuler-x86-aclgraph.tar.gz < 18 hours ago 59.5 MB
llama-b7820-bin-910b-openEuler-aarch64-aclgraph.tar.gz < 18 hours ago 53.8 MB
llama-b7820-bin-310p-openEuler-x86.tar.gz < 18 hours ago 59.5 MB
llama-b7820-bin-310p-openEuler-aarch64.tar.gz < 18 hours ago 53.8 MB
cudart-llama-bin-win-cuda-13.1-x64.zip < 18 hours ago 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 18 hours ago 391.4 MB
b7820 source code.tar.gz < 19 hours ago 28.8 MB
b7820 source code.zip < 19 hours ago 29.8 MB
README.md < 19 hours ago 2.8 kB
Totals: 23 Items   2.4 GB 0
ggml-hexagon: flash-attn opt (#19025) * optimize flash attention kernel by improving score computation and online softmax update * wip * Refactor online softmax update in flash attention kernel for improved performance * Optimize flash attention kernel by replacing float array with HVX_Vector for score computation * wip

macOS/iOS: - macOS Apple Silicon (arm64) - macOS Intel (x64) - iOS XCFramework

Linux: - Ubuntu x64 (CPU) - Ubuntu x64 (Vulkan) - Ubuntu s390x (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)

Source: README.md, updated 2026-01-24