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 9, 11:15 UTC
[CI] Change GPU key to device key for B200 test (#33275)
Signed-off-by: khluu <khluu000@gmail.com>
Kevin H. Luu committed
Jan 28, 2026 at 11:14 UTC
8bdd3979d8c2f15feb475485ba1af1917cefbe5a
1 file changed
+1
-1
.buildkite/test_areas/lm_eval.yaml
+1
-1
@@ -61,7 +61,7 @@ steps:
61
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=evals/gsm8k/configs/moe-refactor/config-h100.txt
62
63
- label: MoE Refactor Integration Test (B200 - TEMPORARY)
64
- gpu: b200
64
+ device: b200
65
optional: true
66
num_devices: 2
67
commands: