Download Latest Version llama-b8192-bin-910b-openEuler-x86-aclgraph.tar.gz (63.1 MB)
Email in envelope

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

Home / b8191
Name Modified Size InfoDownloads / Week
Parent folder
llama-b8191-xcframework.zip < 24 hours ago 169.4 MB
llama-b8191-bin-win-vulkan-x64.zip < 24 hours ago 48.3 MB
llama-b8191-bin-win-sycl-x64.zip < 24 hours ago 121.0 MB
llama-b8191-bin-win-opencl-adreno-arm64.zip < 24 hours ago 25.6 MB
llama-b8191-bin-win-hip-radeon-x64.zip < 24 hours ago 345.0 MB
llama-b8191-bin-win-cuda-13.1-x64.zip < 24 hours ago 148.9 MB
llama-b8191-bin-win-cuda-12.4-x64.zip < 24 hours ago 220.4 MB
llama-b8191-bin-win-cpu-x64.zip < 24 hours ago 31.4 MB
llama-b8191-bin-win-cpu-arm64.zip < 24 hours ago 24.7 MB
llama-b8191-bin-ubuntu-x64.tar.gz < 24 hours ago 25.2 MB
llama-b8191-bin-ubuntu-vulkan-x64.tar.gz < 24 hours ago 42.3 MB
llama-b8191-bin-ubuntu-s390x.tar.gz < 24 hours ago 26.2 MB
llama-b8191-bin-ubuntu-rocm-7.2-x64.tar.gz < 24 hours ago 145.2 MB
llama-b8191-bin-macos-x64.tar.gz < 24 hours ago 88.5 MB
llama-b8191-bin-macos-arm64.tar.gz < 24 hours ago 30.7 MB
llama-b8191-bin-910b-openEuler-x86-aclgraph.tar.gz < 24 hours ago 63.1 MB
llama-b8191-bin-910b-openEuler-aarch64-aclgraph.tar.gz < 24 hours ago 57.0 MB
llama-b8191-bin-310p-openEuler-x86.tar.gz < 24 hours ago 63.1 MB
llama-b8191-bin-310p-openEuler-aarch64.tar.gz < 24 hours ago 57.0 MB
cudart-llama-bin-win-cuda-13.1-x64.zip < 24 hours ago 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 24 hours ago 391.4 MB
b8191 source code.tar.gz 2026-03-03 29.1 MB
b8191 source code.zip 2026-03-03 30.1 MB
README.md 2026-03-03 3.1 kB
Totals: 24 Items   2.6 GB 0
opencl: add optimized q4_1 mm kernel for adreno (#19840) * Add Q4_1 OpenCL Kernels * opencl: refactor transpose * opencl: format * opencl: refactor q4_1 unpack * opencl: move `ggml_cl_mul_mat_q4_1_f32_adreno` * opencl: refactor `ggml_cl_mul_mat_q4_1_f32_adreno` and kernels * opencl: rename kernel files and kernes * opencl: fix build for non adreno * opencl: move code around and format --------- Co-authored-by: Li He <lih@qti.qualcomm.com>

macOS/iOS:

Linux:

Windows:

openEuler:

Source: README.md, updated 2026-03-03