121 lines
3.4 KiB
YAML
121 lines
3.4 KiB
YAML
# AURA Omni deploy profile: Qwen3-ASR -> AURA/Qwen3-VL -> Qwen3-TTS Talker -> Code2Wav.
|
|
#
|
|
# Supported online path is Realtime duplex (`/v1/realtime?duplex=1`).
|
|
# The aura_omni pipeline declares duplex_plugin; DuplexOmniEngine requires
|
|
# session_mode: duplex (same pattern as MiniCPM-o duplex deploys).
|
|
# For Realtime, set async_chunk: true (see aura_omni_duplex_smoke.yaml).
|
|
#
|
|
# Pass `--deploy-config vllm_omni/deploy/aura_omni.yaml` and point the parent
|
|
# `--model` at any local placeholder repo if needed; each stage overrides its
|
|
# own model below.
|
|
pipeline: aura_omni
|
|
session_mode: duplex
|
|
duplex_session:
|
|
max_sessions: 1
|
|
# Default false: safer if this file is ever loaded by turn-based OmniOrchestrator,
|
|
# which does not apply DuplexOmniOrchestrator._stage_receives_async_chunks().
|
|
# Duplex Realtime Stage2→3 (Talker/Code2Wav) still needs async chunks — set
|
|
# async_chunk: true for /v1/realtime?duplex=1 (see aura_omni_duplex_smoke.yaml).
|
|
async_chunk: false
|
|
|
|
connectors:
|
|
connector_of_shared_memory:
|
|
name: SharedMemoryConnector
|
|
extra:
|
|
codec_streaming: true
|
|
connector_get_sleep_s: 0.01
|
|
connector_get_max_wait_first_chunk: 3000
|
|
connector_get_max_wait: 300
|
|
codec_chunk_frames: 25
|
|
codec_left_context_frames: 72
|
|
# initial=1 can stall Code2Wav on the first undersized chunk under duplex.
|
|
initial_codec_chunk_frames: 8
|
|
decode_cudagraph_capture_sizes: [25, 73, 97, 169, 325]
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_seqs: 8
|
|
gpu_memory_utilization: 0.1
|
|
trust_remote_code: true
|
|
enable_prefix_caching: true
|
|
async_scheduling: true
|
|
max_model_len: 8192
|
|
max_num_batched_tokens: 4096
|
|
devices: "0"
|
|
model: Qwen/Qwen3-ASR-1.7B
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 256
|
|
|
|
- stage_id: 1
|
|
max_num_seqs: 4
|
|
gpu_memory_utilization: 0.4
|
|
trust_remote_code: true
|
|
enable_prefix_caching: true
|
|
async_scheduling: true
|
|
max_model_len: 262144
|
|
max_num_batched_tokens: 15360
|
|
devices: "0"
|
|
model: aurateam/AURA
|
|
default_sampling_params:
|
|
temperature: 0.5
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 256
|
|
repetition_penalty: 1.0
|
|
|
|
- stage_id: 2
|
|
max_num_seqs: 8
|
|
gpu_memory_utilization: 0.2
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
async_scheduling: true
|
|
max_num_batched_tokens: 512
|
|
max_model_len: 4096
|
|
devices: "0"
|
|
output_connectors:
|
|
to_stage_3: connector_of_shared_memory
|
|
model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
|
|
# model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
|
|
default_sampling_params:
|
|
temperature: 0.9
|
|
top_k: 50
|
|
max_tokens: 4096
|
|
seed: 42
|
|
repetition_penalty: 1.05
|
|
subtalker_sampling_params:
|
|
do_sample: true
|
|
temperature: 0.9
|
|
top_k: 50
|
|
top_p: 1.0
|
|
|
|
- stage_id: 3
|
|
max_num_seqs: 8
|
|
gpu_memory_utilization: 0.2
|
|
enforce_eager: false
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
async_scheduling: true
|
|
max_num_batched_tokens: 65536
|
|
max_model_len: 65536
|
|
devices: "0"
|
|
input_connectors:
|
|
from_stage_2: connector_of_shared_memory
|
|
model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
|
|
# model: Qwen/Qwen3-TTS-12Hz-1.7B-Base
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 65536
|
|
seed: 42
|
|
repetition_penalty: 1.0
|
|
|
|
platforms:
|
|
npu:
|
|
stages:
|
|
- stage_id: 2
|
|
enforce_eager: true
|