[CI] Harden Qwen3-TTS perf nightly: enable Base voice_clone, add c=64/128, 2-GPU split (#3491)

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
This commit is contained in:
Yueqian Lin authored and GitHub committed 2026-05-14 14:26:59 +08:00
1 parent 0d9d57acd9
commit c4f859bf56
6 files changed
+51 -24

No files matched your search

+2 -2
View File
@@ -172,7 +172,7 @@ steps:
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py tests/e2e/offline_inference/test_qwen3_tts_customvoice.py -m 'advanced_model and cuda' --run-level 'advanced_model'
"
agents:
queue: "gpu_1_queue"
queue: "gpu_4_queue"
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
@@ -193,7 +193,7 @@ steps:
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m 'advanced_model and cuda' --run-level 'advanced_model'
"
agents:
queue: "gpu_1_queue"
queue: "gpu_4_queue"
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+1 -1
View File
@@ -388,7 +388,7 @@ steps:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 1
nvidia.com/gpu: 2
volumeMounts:
- name: devshm
mountPath: /dev/shm
+2 -2
View File
@@ -303,7 +303,7 @@ steps:
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m 'core_model' --run-level 'core_model'
"
agents:
queue: "gpu_1_queue"
queue: "gpu_4_queue"
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
@@ -326,7 +326,7 @@ steps:
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m 'core_model' --run-level 'core_model'
"
agents:
queue: "gpu_1_queue"
queue: "gpu_4_queue"
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT