a3903810fe
Signed-off-by: lishunyang <lishunyang12@163.com> Signed-off-by: reidliu41 <reid201711@gmail.com> Signed-off-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: reidliu41 <reid201711@gmail.com> Co-authored-by: xiaohajiayou <75477391+xiaohajiayou@users.noreply.github.com> Co-authored-by: Alex Brooks <albrooks@redhat.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""Qwen3-TTS pipeline: Talker (text → RVQ codec) → Code2Wav (codec → audio).
|
|
|
|
Chunked vs end-to-end mode is dispatched from ``deploy.async_chunk``.
|
|
"""
|
|
|
|
from vllm_omni.config.stage_config import (
|
|
PipelineConfig,
|
|
StageExecutionType,
|
|
StagePipelineConfig,
|
|
register_pipeline,
|
|
)
|
|
|
|
_PROC = "vllm_omni.model_executor.stage_input_processors.qwen3_tts"
|
|
|
|
QWEN3_TTS_PIPELINE = PipelineConfig(
|
|
model_type="qwen3_tts",
|
|
# Pipeline-level default; the code2wav stage overrides per-stage below.
|
|
model_arch="Qwen3TTSTalkerForConditionalGeneration",
|
|
stages=(
|
|
StagePipelineConfig(
|
|
stage_id=0,
|
|
model_stage="qwen3_tts",
|
|
execution_type=StageExecutionType.LLM_AR,
|
|
input_sources=(),
|
|
owns_tokenizer=True,
|
|
engine_output_type="latent",
|
|
async_chunk_process_next_stage_input_func=(f"{_PROC}.talker2code2wav_async_chunk"),
|
|
sampling_constraints={
|
|
"detokenize": False,
|
|
"stop_token_ids": [2150],
|
|
},
|
|
),
|
|
StagePipelineConfig(
|
|
stage_id=1,
|
|
model_stage="code2wav",
|
|
execution_type=StageExecutionType.LLM_GENERATION,
|
|
input_sources=(0,),
|
|
final_output=True,
|
|
final_output_type="audio",
|
|
engine_output_type="audio",
|
|
model_arch="Qwen3TTSCode2Wav",
|
|
sync_process_input_func=f"{_PROC}.talker2code2wav",
|
|
sampling_constraints={"detokenize": True},
|
|
extras={"tts_args": {"max_instructions_length": 500}},
|
|
),
|
|
),
|
|
)
|
|
|
|
register_pipeline(QWEN3_TTS_PIPELINE)
|