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, 12:00 UTC
[BugFix] Add test_outputs.py to CI pipeline (#28466)
Signed-off-by: Bradley <bradley.b.pitt@gmail.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
usberkeley committed
Nov 12, 2025 at 00:01 UTC
3143eb23fc4e017bc31d11a9756d5a788d6f7e33
2 files changed
+2
.buildkite/test-amd.yaml
+1
@@ -348,6 +348,7 @@ steps:
348
- pytest -v -s -m 'not cpu_test' v1/metrics
349
- pytest -v -s v1/test_oracle.py
350
- pytest -v -s v1/test_request.py
351
+ - pytest -v -s v1/test_outputs.py
352
# Integration test for streaming correctness (requires special branch).
353
- pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
354
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine
.buildkite/test-pipeline.yaml
+1
@@ -329,6 +329,7 @@ steps:
329
- pytest -v -s -m 'not cpu_test' v1/metrics
330
- pytest -v -s v1/test_oracle.py
331
- pytest -v -s v1/test_request.py
332
+ - pytest -v -s v1/test_outputs.py
333
# Integration test for streaming correctness (requires special branch).
334
- pip install -U git+https://github.com/robertgshaw2-redhat/lm-evaluation-harness.git@streaming-api
335
- pytest -v -s entrypoints/openai/correctness/test_lmeval.py::test_lm_eval_accuracy_v1_engine