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 11, 06:15 UTC
[AMD][CI] fix lm eval ci arg (#30911)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Divakar Verma committed
Dec 17, 2025 at 23:18 UTC
82dc338ad609c9a91b0ae764c7961083784cd620
1 file changed
+3
-3
.buildkite/test-amd.yaml
+3
-3
@@ -754,7 +754,7 @@ steps:
754
- vllm/model_executor/layers/quantization
755
autorun_on_main: true
756
commands:
757
- - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
757
+ - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
758
759
- label: OpenAI API correctness # 10min
760
timeout_in_minutes: 15
@@ -1203,7 +1203,7 @@ steps:
1203
- csrc/
1204
- vllm/model_executor/layers/quantization
1205
commands:
1206
- - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt --tp-size=1
1206
+ - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-blackwell.txt
1207
1208
##### 1 GPU test #####
1209
##### multi gpus test #####
@@ -1521,7 +1521,7 @@ steps:
1521
- csrc/
1522
- vllm/model_executor/layers/quantization
1523
commands:
1524
- - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
1524
+ - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
1525
1526
- label: LM Eval Large Models (4 Card)
1527
mirror_hardwares: [amdexperimental, amdproduction]