Files
vllm-omni/examples/offline_inference/qwen3_omni/run_single_prompt_tp.sh
T
2025-11-30 20:01:20 -08:00

6 lines
228 B
Bash

python end2end.py --output-wav output_audio \
--query-type use_audio \
--init-sleep-seconds 90
# init-sleep-seconds works to avoid two vLLM stages initialized at the same time within a card.