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 14, 05:30 UTC
[CI] make all multi-gpu weight loading tests run nightly (#23792)
Signed-off-by: Alex Yun <alexyun04@gmail.com>
Alex committed
Aug 27, 2025 at 23:27 UTC
f48a9af8924ea617a964b1158acc142b64843edb
1 file changed
+1
.buildkite/test-pipeline.yaml
+1
@@ -798,6 +798,7 @@ steps:
798
mirror_hardwares: [amdexperimental]
799
working_dir: "/vllm-workspace/tests"
800
num_gpus: 2
801
+ optional: true
802
source_file_dependencies:
803
- vllm/
804
- tests/weight_loading