b076006c35
Signed-off-by: xiaohajiayou <923390377@qq.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
65 lines
2.0 KiB
YAML
65 lines
2.0 KiB
YAML
# CosyVoice3 deploy: 2-stage talker → flow-matching code2wav.
|
|
#
|
|
# Default mode is async-chunk streaming through SharedMemoryConnector. Pass
|
|
# ``--no-async-chunk`` to the serve CLI for the legacy sync path (stage 1
|
|
# builds flow input from the full speech-token sequence via ``text2flow``).
|
|
# The shared-memory connector definition and input/output_connectors
|
|
# references stay in the yaml unconditionally; the runtime only activates
|
|
# them when ``async_chunk: true``.
|
|
#
|
|
# enforce_eager=true everywhere:
|
|
# * Stage 0 (talker) — cudagraph not verified on this checkpoint.
|
|
# * Stage 1 (code2wav) — CUDA graphs don't work with dynamic conv shapes.
|
|
async_chunk: true
|
|
dtype: float32
|
|
|
|
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: 25
|
|
codec_vocab_size: 6561
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_batched_tokens: 32768
|
|
max_num_seqs: 1
|
|
gpu_memory_utilization: 0.4
|
|
enforce_eager: true
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
devices: "0"
|
|
output_connectors:
|
|
to_stage_1: connector_of_shared_memory
|
|
default_sampling_params:
|
|
max_tokens: 2048
|
|
top_k: 25
|
|
top_p: 0.8
|
|
# near-identity repetition penalty forces vLLM to track
|
|
# output_token_ids for RAS (stop-token logit logsumexp).
|
|
repetition_penalty: 1.0001
|
|
disable_hybrid_kv_cache_manager: true
|
|
mm_processor_cache_gb: 0
|
|
skip_mm_profiling: true
|
|
|
|
- stage_id: 1
|
|
max_num_batched_tokens: 32768
|
|
max_num_seqs: 1
|
|
gpu_memory_utilization: 0.2
|
|
enforce_eager: true
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
max_model_len: 32768
|
|
devices: "0"
|
|
input_connectors:
|
|
from_stage_0: connector_of_shared_memory
|
|
default_sampling_params:
|
|
max_tokens: 2048
|
|
disable_hybrid_kv_cache_manager: true
|
|
skip_mm_profiling: true
|