Download Latest Version llama-b7240-bin-910b-openEuler-x86.tar.gz (33.1 MB)
Email in envelope

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

Home / b7240
Name Modified Size InfoDownloads / Week
Parent folder
llama-b7240-xcframework.zip < 5 hours ago 146.5 MB
0
llama-b7240-xcframework.tar.gz < 5 hours ago 146.6 MB
0
llama-b7240-bin-win-vulkan-x64.zip < 5 hours ago 31.1 MB
0
llama-b7240-bin-win-sycl-x64.zip < 5 hours ago 105.3 MB
0
llama-b7240-bin-win-opencl-adreno-arm64.zip < 5 hours ago 13.3 MB
0
llama-b7240-bin-win-hip-radeon-x64.zip < 5 hours ago 342.1 MB
0
llama-b7240-bin-win-cuda-12.4-x64.zip < 5 hours ago 184.7 MB
0
llama-b7240-bin-win-cpu-x64.zip < 5 hours ago 16.3 MB
0
llama-b7240-bin-win-cpu-arm64.zip < 5 hours ago 12.9 MB
0
llama-b7240-bin-ubuntu-x64.zip < 5 hours ago 15.1 MB
0
llama-b7240-bin-ubuntu-x64.tar.gz < 5 hours ago 15.1 MB
0
llama-b7240-bin-ubuntu-vulkan-x64.zip < 5 hours ago 30.5 MB
0
llama-b7240-bin-ubuntu-vulkan-x64.tar.gz < 5 hours ago 30.5 MB
0
llama-b7240-bin-ubuntu-s390x.zip < 5 hours ago 14.7 MB
0
llama-b7240-bin-ubuntu-s390x.tar.gz < 5 hours ago 17.2 MB
0
llama-b7240-bin-macos-x64.zip < 5 hours ago 32.6 MB
0
llama-b7240-bin-macos-x64.tar.gz < 5 hours ago 32.6 MB
0
llama-b7240-bin-macos-arm64.zip < 5 hours ago 12.8 MB
0
llama-b7240-bin-macos-arm64.tar.gz < 5 hours ago 12.8 MB
0
llama-b7240-bin-910b-openEuler-x86.zip < 5 hours ago 33.1 MB
0
llama-b7240-bin-910b-openEuler-x86.tar.gz < 5 hours ago 33.1 MB
0
llama-b7240-bin-910b-openEuler-aarch64.zip < 5 hours ago 31.5 MB
0
llama-b7240-bin-910b-openEuler-aarch64.tar.gz < 5 hours ago 31.5 MB
0
llama-b7240-bin-310p-openEuler-x86.zip < 5 hours ago 33.1 MB
0
llama-b7240-bin-310p-openEuler-x86.tar.gz < 5 hours ago 33.1 MB
0
llama-b7240-bin-310p-openEuler-aarch64.zip < 5 hours ago 31.5 MB
0
llama-b7240-bin-310p-openEuler-aarch64.tar.gz < 5 hours ago 31.5 MB
0
cudart-llama-bin-win-cuda-12.4-x64.zip < 5 hours ago 391.4 MB
0
b7240 source code.tar.gz < 13 hours ago 27.7 MB
0
b7240 source code.zip < 13 hours ago 28.6 MB
0
README.md < 13 hours ago 2.6 kB
0
Totals: 31 Items   1.9 GB 0

[!WARNING] Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

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) - Windows x64 (Vulkan) - Windows x64 (SYCL) - Windows x64 (HIP)

openEuler: - openEuler x86 (310p) - openEuler x86 (910b) - openEuler aarch64 (310p) - openEuler aarch64 (910b)

vulkan: Reduce temporary memory usage for TOP_K (#17623) - Compute row size for the temp buffer based on the output of the first pass. - Update shader addressing math to use the output row size - Pass the output row size as "ncols_output", what used to be "ncols_output" is now "k" For the common case of K=40 and src0=(200000,1,1,1), this reduces the temporary buffer from about 3.2MB to 500KB.
Source: README.md, updated 2025-12-02