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
Allow buildkite to retry build on agent lost (#2446)
Simon Mo committed
Jan 15, 2024 at 15:43 UTC
bfc072addfba28d9575c372801db840df80d8fb2
1 file changed
+4
.buildkite/test-template.j2
+4
@@ -16,6 +16,10 @@ steps:
16
agents:
17
queue: kubernetes
18
soft_fail: {{ step.soft_fail or false }}
19
+ retry:
20
+ automatic:
21
+ - exit_status: -1 # Agent was lost
22
+ limit: 5
23
plugins:
24
- kubernetes:
25
podSpec: