Download Latest Version llama-b8189-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 / b8184
Name Modified Size InfoDownloads / Week
Parent folder
llama-b8184-xcframework.zip 2026-03-01 169.4 MB
llama-b8184-bin-win-vulkan-x64.zip 2026-03-01 48.3 MB
llama-b8184-bin-win-sycl-x64.zip 2026-03-01 121.0 MB
llama-b8184-bin-win-opencl-adreno-arm64.zip 2026-03-01 25.6 MB
llama-b8184-bin-win-hip-radeon-x64.zip 2026-03-01 345.0 MB
llama-b8184-bin-win-cuda-13.1-x64.zip 2026-03-01 148.9 MB
llama-b8184-bin-win-cuda-12.4-x64.zip 2026-03-01 220.4 MB
llama-b8184-bin-win-cpu-x64.zip 2026-03-01 31.4 MB
llama-b8184-bin-win-cpu-arm64.zip 2026-03-01 24.7 MB
llama-b8184-bin-ubuntu-x64.tar.gz 2026-03-01 25.2 MB
llama-b8184-bin-ubuntu-vulkan-x64.tar.gz 2026-03-01 42.3 MB
llama-b8184-bin-ubuntu-s390x.tar.gz 2026-03-01 26.2 MB
llama-b8184-bin-ubuntu-rocm-7.2-x64.tar.gz 2026-03-01 145.2 MB
llama-b8184-bin-macos-x64.tar.gz 2026-03-01 88.5 MB
llama-b8184-bin-macos-arm64.tar.gz 2026-03-01 30.7 MB
llama-b8184-bin-910b-openEuler-x86-aclgraph.tar.gz 2026-03-01 63.1 MB
llama-b8184-bin-910b-openEuler-aarch64-aclgraph.tar.gz 2026-03-01 57.0 MB
llama-b8184-bin-310p-openEuler-x86.tar.gz 2026-03-01 63.1 MB
llama-b8184-bin-310p-openEuler-aarch64.tar.gz 2026-03-01 57.0 MB
cudart-llama-bin-win-cuda-13.1-x64.zip 2026-03-01 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip 2026-03-01 391.4 MB
b8184 source code.tar.gz 2026-03-01 29.1 MB
b8184 source code.zip 2026-03-01 30.1 MB
README.md 2026-03-01 3.0 kB
Totals: 24 Items   2.6 GB 3
vulkan: improve partial offloading performance on AMD (#19976) * vulkan: fix and enable cpy_tensor_async function * use transfer_queue for async transfers on AMD, synchronize with timeline semaphore * update offload_op logic * fix missing transfer submission * disable async transfer queue on AMD GCN * revert op batch size change * fix cpy_tensor_async checks

macOS/iOS:

Linux:

Windows:

openEuler:

Source: README.md, updated 2026-03-01