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 15, 11:00 UTC
Enabling "Weight Loading Multiple GPU Test - Large Models" (#18020)
Alexei-V-Ivanov-AMD committed
May 12, 2025 at 15:05 UTC
e9c730c9bd0fda1056581bc4cf018871e64fb966
1 file changed
+1
.buildkite/test-pipeline.yaml
+1
@@ -703,6 +703,7 @@ steps:
703
- bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models.txt
704
705
- label: Weight Loading Multiple GPU Test - Large Models # optional
706
+ mirror_hardwares: [amdexperimental]
707
working_dir: "/vllm-workspace/tests"
708
num_gpus: 2
709
gpu: a100