Files
vllm-omni/vllm_omni/deploy/qwen3_tts_high_concurrency_mrv2_b4.yaml

9 lines
329 B
YAML

# Experimental B4 profile. Early first audio can require startup buffering.
# MPS is a separate operator setting and is not enabled by this file.
base_config: qwen3_tts_high_concurrency_mrv2.yaml
connectors:
connector_of_shared_memory:
extra:
decode_batch_max_size: 4
decode_cudagraph_batch_sizes: [1, 2, 3, 4]