Files
vllm-omni/tests/entrypoints
Yueqian Lin ede3dddfdf fix(serving): scope no-async-chunk FINAL_ONLY streaming to qwen3_tts
async_chunk defaults to False in OmniModelConfig, so coercing every
async_chunk=False deploy to FINAL_ONLY for streaming requests would
silently disable incremental delivery for non-Qwen3 models that stream
DELTA-style today. Gate the coercion on _tts_model_type == "qwen3_tts"
(the model this PR validated) and pin the non-qwen3 behavior with a test.

Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
2026-07-03 22:57:27 -07:00
..