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, 03:15 UTC
Downsize CPU jobs to use small queue (#37913)
Signed-off-by: khluu <khluu000@gmail.com> Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Kevin H. Luu committed
Mar 23, 2026 at 20:36 UTC
b2dd75eb481f6d45f6ac902292559026765a1433
3 files changed
+4
-4
.buildkite/test_areas/misc.yaml
+2
-2
@@ -75,7 +75,7 @@ steps:
75
source_file_dependencies:
76
- vllm/
77
- tests/v1
78
- device: cpu
78
+ device: cpu-small
79
commands:
80
# split the test to avoid interference
81
- pytest -v -s -m 'cpu_test' v1/core
@@ -177,7 +177,7 @@ steps:
177
- tests/tool_parsers
178
- tests/transformers_utils
179
- tests/config
180
- device: cpu
180
+ device: cpu-small
181
commands:
182
- python3 standalone_tests/lazy_imports.py
183
- pytest -v -s test_inputs.py
.buildkite/test_areas/models_basic.yaml
+1
-1
@@ -51,7 +51,7 @@ steps:
51
- vllm/
52
- tests/models/test_utils.py
53
- tests/models/test_vision.py
54
- device: cpu
54
+ device: cpu-small
55
commands:
56
- pytest -v -s models/test_utils.py models/test_vision.py
57
.buildkite/test_areas/models_multimodal.yaml
+1
-1
@@ -70,7 +70,7 @@ steps:
70
- vllm/
71
- tests/models/multimodal
72
- tests/models/registry.py
73
- device: cpu
73
+ device: cpu-medium
74
commands:
75
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
76
- pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py