feat: support offloading sd to multi devs #658
thxCodeci.yml
on: push
Matrix: darwin-metal
Matrix: darwin
Matrix: linux-cann
Matrix: linux-cuda
Matrix: linux-dtk
Matrix: linux-hip
Matrix: linux-musa
Matrix: linux-oneapi
Matrix: linux
Matrix: windows-cuda
Matrix: windows-hip
Matrix: windows-oneapi
Matrix: windows
release
0s
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
llama-box-darwin-amd64-avx2
|
5.15 MB |
|
|
llama-box-darwin-amd64-metal-3.0
|
5.25 MB |
|
|
llama-box-darwin-arm64-metal-3.0
|
5.3 MB |
|
|
llama-box-linux-amd64-avx2
|
10.8 MB |
|
|
llama-box-linux-amd64-avx512
|
12.2 MB |
|
|
llama-box-linux-amd64-cann-8.0
|
6.41 MB |
|
|
llama-box-linux-amd64-cann-8.0-310p
|
6.41 MB |
|
|
llama-box-linux-amd64-cann-8.0-openeuler20.03
|
6.15 MB |
|
|
llama-box-linux-amd64-cann-8.0-openeuler20.03-310p
|
6.15 MB |
|
|
llama-box-linux-amd64-cuda-11.8
|
133 MB |
|
|
llama-box-linux-amd64-cuda-12.4
|
132 MB |
|
|
llama-box-linux-amd64-dtk-24.04
|
40.3 MB |
|
|
llama-box-linux-amd64-hip-6.2
|
77.7 MB |
|
|
llama-box-linux-amd64-musa-rc3.1
|
23.4 MB |
|
|
llama-box-linux-amd64-oneapi-2025.0
|
6.19 MB |
|
|
llama-box-linux-arm64-cann-8.0
|
6.61 MB |
|
|
llama-box-linux-arm64-cann-8.0-310p
|
6.61 MB |
|
|
llama-box-linux-arm64-cann-8.0-openeuler20.03
|
6.41 MB |
|
|
llama-box-linux-arm64-cann-8.0-openeuler20.03-310p
|
6.4 MB |
|
|
llama-box-linux-arm64-neon
|
6.44 MB |
|
|
llama-box-windows-amd64-avx2
|
4.23 MB |
|
|
llama-box-windows-amd64-avx512
|
4.24 MB |
|
|
llama-box-windows-amd64-cuda-11.8
|
131 MB |
|
|
llama-box-windows-amd64-cuda-12.4
|
130 MB |
|
|
llama-box-windows-amd64-hip-6.2
|
37.4 MB |
|
|
llama-box-windows-amd64-oneapi-2025.0
|
5.13 MB |
|
|
llama-box-windows-arm64-neon
|
3.03 MB |
|