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 3, 06:45 UTC
[ci] Move language models tests (hybrid) back to L4 (#43129)
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
May 19, 2026 at 11:51 UTC
a65093c1a39a8ddd8455365128ecbe259350e22c
1 file changed
-1
.buildkite/test_areas/models_language.yaml
-1
@@ -34,7 +34,6 @@ steps:
34
torch_nightly: {}
35
36
- label: Language Models Tests (Hybrid) %N
37
- device: h200_35gb
37
key: language-models-tests-hybrid
38
timeout_in_minutes: 75
39
source_file_dependencies: