A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 01:45 UTC
[CI] use ccache actions properly in release workflow (#4629)
Simon Mo committed
May 6, 2024 at 15:23 UTC
e186d37cb135107a09cd684e4fa2cf30c0ce6f28
1 file changed
+3
.github/workflows/publish.yml
+3
@@ -58,6 +58,9 @@ jobs:
58
59
- name: Setup ccache
60
uses: hendrikmuhs/ccache-action@v1.2
61
+ with:
62
+ create-symlink: true
63
+ key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
64
65
- name: Set up Linux Env
66
if: ${{ runner.os == 'Linux' }}