19 lines
374 B
YAML
19 lines
374 B
YAML
# Opt-in CUDA Model Runner V2 profile. The base profile retains V1.
|
|
base_config: qwen3_tts.yaml
|
|
model_runner: v2
|
|
|
|
platforms:
|
|
npu:
|
|
model_runner: v1
|
|
xpu:
|
|
model_runner: v1
|
|
rocm:
|
|
model_runner: v1
|
|
musa:
|
|
model_runner: v1
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
# Bound per-step prefill work, matching the high-concurrency TTS profile.
|
|
max_num_batched_tokens: 512
|