30 lines
788 B
YAML
30 lines
788 B
YAML
# Opt-in CUDA Model Runner V2 profile. The base profile retains V1.
|
|
base_config: qwen3_tts_high_concurrency.yaml
|
|
model_runner: v2
|
|
|
|
platforms:
|
|
npu:
|
|
model_runner: v1
|
|
xpu:
|
|
model_runner: v1
|
|
rocm:
|
|
model_runner: v1
|
|
musa:
|
|
model_runner: v1
|
|
|
|
connectors:
|
|
connector_of_shared_memory:
|
|
extra:
|
|
talker_first_audio: true
|
|
# Keep unqualified prefix-graph optimizations disabled in this profile.
|
|
code_predictor_prefix_graphs: false
|
|
ref_audio_artifact_cache_max_entries: 1024
|
|
# Opt-in B2 codec graphs. Validate quality for the deployment workload.
|
|
decode_batch_max_size: 2
|
|
decode_cudagraph_batch_sizes: [1, 2]
|
|
|
|
stages:
|
|
- stage_id: 1
|
|
# Enable the decoder's inner graphs; the generation runner stays eager.
|
|
enforce_eager: false
|