feat[vLLM × v5]: Add audio support for the Transformers backend (#39330)

Signed-off-by: Harshal Janjani <harshaljanjani@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Harshal Janjani
2026-07-25 04:20:58 -07:00
committed by GitHub
co-authored by Harry Mellor mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent ca0defa343
commit b9b6306ebe
8 changed files with 682 additions and 152 deletions
@@ -452,6 +452,14 @@ def test_processing_correctness(
"audio placeholders from processed audio lengths. Its vLLM "
"processor paths are covered by test_moss_audio.py."
)
# TODO: Remove when transformers 5.15.0 is released, which contains
# https://github.com/huggingface/transformers/pull/47483.
if model_id == "microsoft/VibeVoice-ASR-HF":
pytest.skip(
"VibeVoice ASR requires audio as a positional argument and hence "
"cannot pass the processing correctness test as is. Its generation "
"is covered by test_transformers_audio.py."
)
if model_id == "lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct":
pytest.skip(
"LLaVA-OneVision-2 video processing routes frames through custom "