Download Latest Version llama-b10106-bin-win-openvino-2026.2.1-x64.zip (80.4 MB)
Email in envelope

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

Home / b10098
Name Modified Size InfoDownloads / Week
Parent folder
llama-b10098-xcframework.zip < 24 hours ago 259.9 MB
llama-b10098-ui.tar.gz < 24 hours ago 3.1 MB
llama-b10098-bin-win-vulkan-x64.zip < 24 hours ago 33.5 MB
llama-b10098-bin-win-sycl-x64.zip < 24 hours ago 119.7 MB
llama-b10098-bin-win-openvino-2026.2.1-x64.zip < 24 hours ago 80.4 MB
llama-b10098-bin-win-opencl-adreno-arm64.zip < 24 hours ago 12.8 MB
llama-b10098-bin-win-hip-radeon-x64.zip < 24 hours ago 320.8 MB
llama-b10098-bin-win-cuda-13.3-x64.zip < 24 hours ago 146.0 MB
llama-b10098-bin-win-cuda-12.4-x64.zip < 24 hours ago 249.9 MB
llama-b10098-bin-win-cpu-x64.zip < 24 hours ago 18.2 MB
llama-b10098-bin-win-cpu-arm64.zip < 24 hours ago 12.1 MB
llama-b10098-bin-ubuntu-x64.tar.gz < 24 hours ago 16.3 MB
llama-b10098-bin-ubuntu-vulkan-x64.tar.gz < 24 hours ago 32.2 MB
llama-b10098-bin-ubuntu-vulkan-arm64.tar.gz < 24 hours ago 26.3 MB
llama-b10098-bin-ubuntu-sycl-fp32-x64.tar.gz < 24 hours ago 52.6 MB
llama-b10098-bin-ubuntu-sycl-fp16-x64.tar.gz < 24 hours ago 52.8 MB
llama-b10098-bin-ubuntu-s390x.tar.gz < 24 hours ago 15.1 MB
llama-b10098-bin-ubuntu-rocm-7.2-x64.tar.gz < 24 hours ago 125.1 MB
llama-b10098-bin-ubuntu-openvino-2026.2.1-x64.tar.gz < 24 hours ago 101.6 MB
llama-b10098-bin-ubuntu-arm64.tar.gz < 24 hours ago 13.2 MB
llama-b10098-bin-macos-x64.tar.gz < 24 hours ago 11.1 MB
llama-b10098-bin-macos-arm64.tar.gz < 24 hours ago 10.8 MB
llama-b10098-bin-android-arm64.tar.gz < 24 hours ago 75.1 MB
cudart-llama-bin-win-cuda-13.3-x64.zip < 24 hours ago 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 24 hours ago 391.4 MB
b10098 source code.tar.gz 2026-07-22 36.3 MB
b10098 source code.zip 2026-07-22 38.0 MB
README.md 2026-07-22 4.1 kB
Totals: 28 Items   2.6 GB 0
hexagon: activation ops update (#25974) * hex-geglu: optimized all-in-one geglu microkernel * hex-geglu: enable non-contiguous src and strided DMA * hex-act: enable non-contiguous srs and strided DMA for rest of ACT ops * hex-act: generalize GLU per-thread functions via DEFINE_GLU_PER_THREAD macro * hexagon: move UNARY_SILU and UNARY_GELU to unary-ops * hex-act: replace the generic ops_context scratchpad usage with a local htp_vtcm_layout computation per act op. --------- Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

Website:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

Source: README.md, updated 2026-07-22