anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Refactor] Migrate Voxtral TTS XPU stage config to --deploy-config (#5467)

Browse Source 
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
This commit is contained in:
Joshna-Medisetty authored and GitHub committed 2026-07-28 07:35:35 +08:00
1 parent d4a5eaac90
commit 807db6efd7
4 files changed
+14 -109
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/e2e/offline_inference/test_voxtral_tts_expansion.py
+1 -1
View File
@@ -58,7 +58,7 @@ def _compose_request(model_name: str, text: str, voice: str) -> dict:
@pytest.mark.parametrize("omni_runner_function", [_OMNI_RUNNER_PARAM], indirect=True)
@hardware_test(res={"cuda": "L4"}, num_cards=1)
@hardware_test(res={"cuda": "L4", "xpu": "B60"}, num_cards=1)
def test_voxtral_tts_offline_basic(omni_runner_function: OmniRunner) -> None:
"""Offline sync path; function-scoped runner so AsyncOmni test does not overlap a live Omni."""
omni = omni_runner_function.omni
tests/e2e/online_serving/test_voxtral_tts_expansion.py
+2 -2
View File
@@ -30,7 +30,7 @@ pytestmark = [
]
@hardware_test(res={"cuda": "L4"}, num_cards=1)
@hardware_test(res={"cuda": "L4", "xpu": "B60"}, num_cards=1)
def test_speech_english_basic(omni_server, openai_client) -> None:
"""Test basic English TTS generation."""
openai_client.send_audio_speech_request(
@@ -46,7 +46,7 @@ def test_speech_english_basic(omni_server, openai_client) -> None:
)
@hardware_test(res={"cuda": "L4"}, num_cards=1)
@hardware_test(res={"cuda": "L4", "xpu": "B60"}, num_cards=1)
def test_speech_english_streaming(omni_server, openai_client) -> None:
"""Test basic streaming English TTS generation (PCM via streaming API)."""
openai_client.send_audio_speech_request(