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, 00:45 UTC
[ROCm][CI] Rename filepath test to point to correct file (#38102)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Mar 25, 2026 at 07:05 UTC
04417ecd5f492c2c216faa7200a0589f7241a302
1 file changed
+1
-1
.buildkite/test-amd.yaml
+1
-1
@@ -2526,7 +2526,7 @@ steps:
2526
- pytest -v -s -x lora/test_llm_with_multi_loras.py
2527
- pytest -v -s -x lora/test_olmoe_tp.py
2528
- pytest -v -s -x lora/test_gptoss_tp.py
2529
- - pytest -v -s -x lora/test_qwen35_densemoel_lora.py
2529
+ - pytest -v -s -x lora/test_qwen35_densemodel_lora.py
2530
2531
2532
- label: Weight Loading Multiple GPU # 7.5m