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 13, 09:30 UTC
[CI] Introduce autorun_on_main feature (#27836)
Signed-off-by: Huamin Li <3ericli@gmail.com>
Huamin Li committed
Nov 12, 2025 at 00:51 UTC
c748355e0d55c98d5458aebbd680ce684c87c9bb
1 file changed
+3
-1
.buildkite/test-pipeline.yaml
+3
-1
@@ -25,6 +25,7 @@
25
# and $$BUILDKITE_PARALLEL_JOB_COUNT environment variables.
26
# working_dir(str): specify the place where the command should execute, default to /vllm-workspace/tests
27
# source_file_dependencies(list): the list of prefixes to opt-in the test for, if empty, the test will always run.
28
+# autorun_on_main (bool): default to false, if true, the test will run automatically when commit is pushed to main branch.
29
30
# When adding a test
31
# - If the test belongs to an existing group, add it there
@@ -606,6 +607,7 @@ steps:
607
source_file_dependencies:
608
- csrc/
609
- vllm/model_executor/layers/quantization
610
+ autorun_on_main: true
611
commands:
612
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
613
@@ -939,7 +941,7 @@ steps:
941
# this runner has 2 GPUs available even though num_gpus=2 is not set
942
- pytest -v -s tests/compile/test_fusion_all_reduce.py
943
# Limit to Inductor partition, no custom ops, and allreduce & attn fusion to reduce running time
942
- # Wrap with quotes to escape yaml
944
+ # Wrap with quotes to escape yaml
945
- "pytest -v -s tests/compile/test_fusions_e2e.py::test_tp2_attn_quant_allreduce_rmsnorm -k 'True and Llama-3.1 and -quant_fp8 and -rms_norm'"
946
947
- label: Blackwell Fusion E2E Tests # 30 min