fix: embeddings/rerank processing #576
thxCodeci.yml
on: push
Matrix: darwin-metal
Matrix: darwin
Matrix: linux-cann
Matrix: linux-cuda
Matrix: linux-hip
Matrix: linux-musa
Matrix: linux-oneapi
Matrix: linux
Matrix: windows-cuda
Matrix: windows-hip
Matrix: windows-oneapi
Matrix: windows
release
12s
Artifacts
Produced during runtime
| Name | Size | |
|---|---|---|
|
llama-box-darwin-amd64-avx2
|
3.08 MB |
|
|
llama-box-darwin-amd64-metal-3.0
|
3.18 MB |
|
|
llama-box-darwin-arm64-metal-3.0
|
2.92 MB |
|
|
llama-box-linux-amd64-avx2
|
8.49 MB |
|
|
llama-box-linux-amd64-avx512
|
9.8 MB |
|
|
llama-box-linux-amd64-cann-8.0
|
3.97 MB |
|
|
llama-box-linux-amd64-cann-8.0-310p
|
3.97 MB |
|
|
llama-box-linux-amd64-cann-8.0-openeuler20.03
|
3.8 MB |
|
|
llama-box-linux-amd64-cann-8.0-openeuler20.03-310p
|
3.8 MB |
|
|
llama-box-linux-amd64-cuda-11.8
|
130 MB |
|
|
llama-box-linux-amd64-cuda-12.4
|
129 MB |
|
|
llama-box-linux-amd64-hip-6.1
|
81.3 MB |
|
|
llama-box-linux-amd64-musa-rc3.1
|
21.3 MB |
|
|
llama-box-linux-amd64-oneapi-2025.0
|
4.17 MB |
|
|
llama-box-linux-arm64-cann-8.0
|
3.8 MB |
|
|
llama-box-linux-arm64-cann-8.0-310p
|
3.79 MB |
|
|
llama-box-linux-arm64-cann-8.0-openeuler20.03
|
3.7 MB |
|
|
llama-box-linux-arm64-cann-8.0-openeuler20.03-310p
|
3.7 MB |
|
|
llama-box-linux-arm64-neon
|
3.62 MB |
|
|
llama-box-windows-amd64-avx2
|
2.44 MB |
|
|
llama-box-windows-amd64-avx512
|
2.45 MB |
|
|
llama-box-windows-amd64-cuda-11.8
|
129 MB |
|
|
llama-box-windows-amd64-cuda-12.4
|
128 MB |
|
|
llama-box-windows-amd64-hip-6.1
|
37.9 MB |
|
|
llama-box-windows-amd64-oneapi-2025.0
|
3.31 MB |
|
|
llama-box-windows-arm64-neon
|
2.34 MB |
|