10 lines
389 B
YAML
10 lines
389 B
YAML
# MOSS-TTS-Local-Transformer-v1.5 3-NPU deploy: Stage0 talker on NPU 0, Stage1 codec x2 replicas on NPU 1,2.
|
|
# Splits AR (talker+depth) and codec across 3 devices, with 2 codec replicas for doubled codec throughput.
|
|
# Launch: vllm-omni serve ... --deploy-config moss_tts_local_3npu.yaml
|
|
base_config: moss_tts_local_2npu.yaml
|
|
|
|
stages:
|
|
- stage_id: 1
|
|
devices: "1,2"
|
|
num_replicas: 2
|