Nick CaoandClaude
f2edb81a59
Signed-off-by: Nick Cao <ncao@redhat.com> Co-authored-by: Claude <noreply@anthropic.com>
93 lines
2.5 KiB
YAML
93 lines
2.5 KiB
YAML
model_type: qwen3_tts
|
|
async_chunk: true
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
model_stage: qwen3_tts
|
|
stage_type: llm
|
|
is_comprehension: true
|
|
input_sources: []
|
|
worker_type: ar
|
|
scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler
|
|
runtime:
|
|
devices: "0"
|
|
engine_args:
|
|
max_num_seqs: 10
|
|
model_arch: Qwen3TTSTalkerForConditionalGeneration
|
|
hf_overrides:
|
|
architectures: [Qwen3TTSTalkerForConditionalGeneration]
|
|
enforce_eager: false
|
|
trust_remote_code: true
|
|
async_scheduling: true
|
|
enable_prefix_caching: false
|
|
engine_output_type: latent
|
|
gpu_memory_utilization: 0.08
|
|
distributed_executor_backend: "mp"
|
|
max_num_batched_tokens: 512
|
|
max_model_len: 4096
|
|
custom_process_next_stage_input_func: vllm_omni.model_executor.stage_input_processors.qwen3_tts.talker2code2wav_async_chunk
|
|
output_connectors:
|
|
to_stage_1: connector_of_shared_memory
|
|
default_sampling_params:
|
|
temperature: 0.9
|
|
top_k: 50
|
|
max_tokens: 4096
|
|
seed: 42
|
|
detokenize: false
|
|
repetition_penalty: 1.05
|
|
stop_token_ids: [2150]
|
|
|
|
- stage_id: 1
|
|
model_stage: code2wav
|
|
stage_type: llm
|
|
input_sources: [0]
|
|
worker_type: generation
|
|
scheduler_cls: vllm_omni.core.sched.omni_generation_scheduler.OmniGenerationScheduler
|
|
final_output: true
|
|
final_output_type: audio
|
|
runtime:
|
|
devices: "0"
|
|
engine_args:
|
|
max_num_seqs: 1
|
|
model_arch: Qwen3TTSCode2Wav
|
|
hf_overrides:
|
|
architectures: [Qwen3TTSCode2Wav]
|
|
enforce_eager: true
|
|
trust_remote_code: true
|
|
async_scheduling: true
|
|
enable_prefix_caching: false
|
|
engine_output_type: audio
|
|
gpu_memory_utilization: 0.08
|
|
distributed_executor_backend: "mp"
|
|
max_num_batched_tokens: 65536
|
|
max_model_len: 65536
|
|
input_connectors:
|
|
from_stage_0: connector_of_shared_memory
|
|
tts_args:
|
|
max_instructions_length: 500
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 65536
|
|
seed: 42
|
|
detokenize: true
|
|
repetition_penalty: 1.0
|
|
|
|
connectors:
|
|
connector_of_shared_memory:
|
|
name: SharedMemoryConnector
|
|
extra:
|
|
shm_threshold_bytes: 65536
|
|
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
|
|
# Match the decoder sliding attention window to avoid chunk-boundary noise.
|
|
codec_left_context_frames: 72
|
|
|
|
edges:
|
|
- from: 0
|
|
to: 1
|