@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 99722d5f0e

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 14, 05:30 UTC

[CI] Remove forbidden slash (#27112)

Signed-off-by: NickLucche <nlucches@redhat.com>

Nicolò Lucchesi committed Oct 17, 2025 at 18:38 UTC 99722d5f0ef06f7face6cf102199ad92671ede90

1 file changed +1 -1

.buildkite/test-pipeline.yaml

+1 -1

@@ -1085,7 +1085,7 @@ steps:

1085 commands:

1086 - bash weight_loading/run_model_weight_loading_test.sh -c weight_loading/models-large.txt

1087

1088 -- label: NixlConnector P/D accuracy tests (Distributed) # 30min

1088 +- label: NixlConnector PD accuracy tests (Distributed) # 30min

1089 timeout_in_minutes: 30

1090 working_dir: "/vllm-workspace/tests"

1091 num_gpus: 4