@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 11d652bd4f
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, 03:00 UTC

[CI] Move CPU/AMD tests to after wait (#4123)

Cade Daniel committed Apr 16, 2024 at 22:53 UTC 11d652bd4f6f81d09638399885099b78a4e3b9c8
1 file changed +8 -7
.buildkite/test-template.j2
+8 -7
@@ -3,13 +3,6 @@
3 {% set default_working_dir = "/vllm-workspace/tests" %}
4
5 steps:
6 - - label: "AMD Test"
7 - agents:
8 - queue: amd
9 - command: bash .buildkite/run-amd-test.sh
10 -
11 - - label: "CPU Test"
12 - command: bash .buildkite/run-cpu-test.sh
6
7 - label: ":docker: build image"
8 commands:
@@ -23,6 +16,14 @@ steps:
16 limit: 5
17 - wait
18
19 + - label: "AMD Test"
20 + agents:
21 + queue: amd
22 + command: bash .buildkite/run-amd-test.sh
23 +
24 + - label: "CPU Test"
25 + command: bash .buildkite/run-cpu-test.sh
26 +
27 {% for step in steps %}
28 - label: "{{ step.label }}"
29 agents: