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, 16:30 UTC
[ROCm] [CI] Reduce Resource of two test groups (#34059)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
TJian committed
Feb 8, 2026 at 15:17 UTC
785cf28ffffeddeecf79018074a222b7c5938f9c
1 file changed
+2
-2
.buildkite/test-amd.yaml
+2
-2
@@ -754,7 +754,7 @@ steps:
754
- label: Benchmarks # 11min
755
timeout_in_minutes: 20
756
mirror_hardwares: [amdexperimental, amdproduction]
757
- agent_pool: mi325_8
757
+ agent_pool: mi325_1
758
# grade: Blocking
759
working_dir: "/vllm-workspace/.buildkite"
760
source_file_dependencies:
@@ -765,7 +765,7 @@ steps:
765
- label: Benchmarks CLI Test # 7min
766
timeout_in_minutes: 20
767
mirror_hardwares: [amdexperimental, amdproduction]
768
- agent_pool: mi325_8
768
+ agent_pool: mi325_1
769
# grade: Blocking
770
source_file_dependencies:
771
- vllm/