biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

Browse Source 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-03-13 14:16:02 -07:00
committed by GitHub
parent 0005d2a3c9
commit f1816fb192
18 changed files with 81 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.buildkite/test_areas/model_runner_v2.yaml
View File

@@ -18,9 +18,9 @@ steps:
- pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics"
# This requires eager until we sort out CG correctness issues.
# TODO: remove ENFORCE_EAGER here after https://github.com/vllm-project/vllm/pull/32936 is merged.
- ENFORCE_EAGER=1 pytest -v -s v1/e2e/test_async_scheduling.py -k "not ngram"
- pytest -v -s v1/e2e/test_context_length.py
- pytest -v -s v1/e2e/test_min_tokens.py
- ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram"
- pytest -v -s v1/e2e/general/test_context_length.py
- pytest -v -s v1/e2e/general/test_min_tokens.py
# Temporary hack filter to exclude ngram spec decoding based tests.
- pytest -v -s v1/entrypoints/llm/test_struct_output_generate.py -k "xgrammar and not speculative_config6 and not speculative_config7 and not speculative_config8 and not speculative_config0"
@@ -102,9 +102,9 @@ steps:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/v1/spec_decode/test_max_len.py
- tests/v1/e2e/test_spec_decode.py
- tests/v1/e2e/spec_decode/test_spec_decode.py
commands:
- set -x
- export VLLM_USE_V2_MODEL_RUNNER=1
- pytest -v -s v1/spec_decode/test_max_len.py -k "eagle or mtp"
- pytest -v -s v1/e2e/test_spec_decode.py -k "eagle or mtp"
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle or mtp"