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 8, 02:30 UTC
[CI] temporarily disable multi-node tests (#34825)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Robert Shaw <robshaw@redhat.com>
Robert Shaw committed
Feb 18, 2026 at 11:32 UTC
25e2e136ef33735039cf6632f8f7293be423f7ba
1 file changed
+1
.buildkite/test_areas/distributed.yaml
+1
@@ -165,6 +165,7 @@ steps:
165
num_devices: 2
166
num_nodes: 2
167
no_plugin: true
168
+ optional: true # TODO: revert once infra issue solved
169
source_file_dependencies:
170
- vllm/distributed/
171
- vllm/engine/