examples/offline_inference/qwen3_omni/run_single_prompt_tp.sh

python end2end.py --output-wav output_audio \
                  --query-type use_audio \
                  --stage-init-timeout 300

# stage-init-timeout sets the maximum wait to avoid two vLLM stages initializing at the same time on the same card.
[Bugfix] Remove mandatory flash-attn dependency and optimzie docs (#113 ) 2025-11-30 18:20:44 +08:00			`python end2end.py --output-wav output_audio \`
			`--query-type use_audio \`
[Feature] Control the stage init timeout threshold by --stage-init-timeout (#393 ) 2025-12-30 23:37:10 +08:00			`--stage-init-timeout 300`
[Bugfix] Remove mandatory flash-attn dependency and optimzie docs (#113 ) 2025-11-30 18:20:44 +08:00
[Feature] Control the stage init timeout threshold by --stage-init-timeout (#393 ) 2025-12-30 23:37:10 +08:00			`# stage-init-timeout sets the maximum wait to avoid two vLLM stages initializing at the same time on the same card.`