xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 00:06:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI] Introduce autorun_on_main feature (#27836)

Browse Source 
Signed-off-by: Huamin Li <3ericli@gmail.com>
This commit is contained in:
Huamin Li 2025-11-12 00:51:19 -08:00 committed by GitHub
parent 91864b79b3
commit c748355e0d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.buildkite/test-pipeline.yaml
View File

@ -25,6 +25,7 @@
# and $$BUILDKITE_PARALLEL_JOB_COUNT environment variables. # and $$BUILDKITE_PARALLEL_JOB_COUNT environment variables.
# working_dir(str): specify the place where the command should execute, default to /vllm-workspace/tests # working_dir(str): specify the place where the command should execute, default to /vllm-workspace/tests
# source_file_dependencies(list): the list of prefixes to opt-in the test for, if empty, the test will always run. # source_file_dependencies(list): the list of prefixes to opt-in the test for, if empty, the test will always run.
# autorun_on_main (bool): default to false, if true, the test will run automatically when commit is pushed to main branch.
# When adding a test # When adding a test
# - If the test belongs to an existing group, add it there # - If the test belongs to an existing group, add it there
@ -606,6 +607,7 @@ steps:
source_file_dependencies: source_file_dependencies:
- csrc/ - csrc/
- vllm/model_executor/layers/quantization - vllm/model_executor/layers/quantization
autorun_on_main: true
commands: commands:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1 - pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt --tp-size=1
@ -939,7 +941,7 @@ steps:
# this runner has 2 GPUs available even though num_gpus=2 is not set # this runner has 2 GPUs available even though num_gpus=2 is not set
- pytest -v -s tests/compile/test_fusion_all_reduce.py - pytest -v -s tests/compile/test_fusion_all_reduce.py
# Limit to Inductor partition, no custom ops, and allreduce & attn fusion to reduce running time # Limit to Inductor partition, no custom ops, and allreduce & attn fusion to reduce running time
# Wrap with quotes to escape yaml # Wrap with quotes to escape yaml
- "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'" - "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'"
- label: Blackwell Fusion E2E Tests # 30 min - label: Blackwell Fusion E2E Tests # 30 min