@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / bfc072addf
Fork 0

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: