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 4, 02:30 UTC
[CI] Narrow Platform Tests (CUDA) source dependencies (#42054)
Signed-off-by: khluu <khluu000@gmail.com>
Kevin H. Luu committed
May 8, 2026 at 14:54 UTC
f4dd5c116cba84f5bba80a4e84908fa8766f5026
1 file changed
+5
-1
.buildkite/test_areas/cuda.yaml
+5
-1
@@ -7,7 +7,11 @@ steps:
7
timeout_in_minutes: 15
8
device: h200_18gb
9
source_file_dependencies:
10
- - vllm/
10
+ - vllm/envs.py
11
+ - vllm/logger.py
12
+ - vllm/platforms/
13
+ - vllm/plugins/
14
+ - vllm/utils/
15
- tests/cuda
16
commands:
17
- pytest -v -s cuda/test_cuda_context.py