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 16, 23:15 UTC
[ci] Use small_cpu_queue for doc build (#5331)
Signed-off-by: kevin <kevin@anyscale.com>
Kevin H. Luu committed
Jun 10, 2024 at 09:21 UTC
f7f9c5f97b4dd206a3cd9c65729a1c807ac82f50
1 file changed
+3
-1
.buildkite/test-template-aws.j2
+3
-1
@@ -22,7 +22,9 @@ steps:
22
{% for step in steps %}
23
- label: "{{ step.label }}"
24
agents:
25
- {% if step.no_gpu %}
25
+ {% if step.label == "Documentation Build" %}
26
+ queue: small_cpu_queue
27
+ {% elif step.no_gpu %}
28
queue: cpu_queue
29
{% elif step.num_gpus == 2 or step.num_gpus == 4 %}
30
queue: gpu_4_queue