@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 19cb4716ee
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, 01:45 UTC

[CI] Add retry for agent lost (#4633)

Cade Daniel committed May 6, 2024 at 16:18 UTC 19cb4716ee700e5d8baa64d7cf14fb5da3737f6d
1 file changed +4
.buildkite/test-template.j2
+4
@@ -14,6 +14,8 @@ steps:
14 automatic:
15 - exit_status: -1 # Agent was lost
16 limit: 5
17 + - exit_status: -10 # Agent was lost
18 + limit: 5
19 - wait
20
21 - group: "AMD Tests"
@@ -53,6 +55,8 @@ steps:
55 automatic:
56 - exit_status: -1 # Agent was lost
57 limit: 5
58 + - exit_status: -10 # Agent was lost
59 + limit: 5
60 plugins:
61 - kubernetes:
62 podSpec: