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, 05:30 UTC
ci: retry on build failure as well (#2457)
Simon Mo committed
Jan 16, 2024 at 12:51 UTC
8cd5a992bffff40434dac6c233767e4fa6359183
1 file changed
+4
.buildkite/test-template.j2
+4
@@ -9,6 +9,10 @@ steps:
9
- "docker push {{ docker_image }}"
10
env:
11
DOCKER_BUILDKIT: "1"
12
+ retry:
13
+ automatic:
14
+ - exit_status: -1 # Agent was lost
15
+ limit: 5
16
- wait
17
18
{% for step in steps %}