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 6, 19:15 UTC
[ROCm][CI] Corrected the GPT-OSS test root path (#36711)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Mar 13, 2026 at 02:53 UTC
99a57bdf74a27bcb7f7e9324a9387f8e098a2fab
1 file changed
+2
-2
.buildkite/test-amd.yaml
+2
-2
@@ -2983,7 +2983,7 @@ steps:
2983
2984
- label: ROCm GPT-OSS Eval
2985
timeout_in_minutes: 60
2986
- working_dir: "/vllm-workspace/"
2986
+ working_dir: "/vllm-workspace/tests"
2987
agent_pool: mi325_1
2988
mirror_hardwares: [amdexperimental, amdproduction]
2989
optional: true # run on nightlies
@@ -4744,7 +4744,7 @@ steps:
4744
4745
- label: ROCm GPT-OSS Eval
4746
timeout_in_minutes: 60
4747
- working_dir: "/vllm-workspace/"
4747
+ working_dir: "/vllm-workspace/tests"
4748
agent_pool: mi355_1
4749
mirror_hardwares: [amdexperimental, amdproduction]
4750
optional: true # run on nightlies