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: