77 lines
2.1 KiB
YAML
77 lines
2.1 KiB
YAML
# Fish Speech S2 Pro deploy: async-chunk streaming slow_ar → dac_decoder.
|
||
# Verified on 1× H20.
|
||
# Registry key and filename use the HF ``model_type=fish_qwen3_omni`` for
|
||
# auto-detection; human-readable "fish_speech" stays as the source directory.
|
||
async_chunk: true
|
||
enable_chunked_prefill: 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
|
||
# ~21 Hz codec; 25 frames ≈ 1.16s of audio.
|
||
codec_chunk_frames: 25
|
||
codec_left_context_frames: 25
|
||
initial_codec_chunk_frames: 4
|
||
|
||
stages:
|
||
- stage_id: 0
|
||
max_num_seqs: 4
|
||
gpu_memory_utilization: 0.6
|
||
enforce_eager: false
|
||
trust_remote_code: true
|
||
enable_prefix_caching: false
|
||
async_scheduling: false
|
||
# vLLM >=0.19 requires max_num_batched_tokens >= max_model_len when
|
||
# enable_chunked_prefill=false. Bumped from legacy 3072 to match
|
||
# max_model_len; chunked prefill stays off because the SlowAR decode
|
||
# loop isn't chunked-prefill-safe.
|
||
max_num_batched_tokens: 16384
|
||
max_model_len: 16384
|
||
devices: "0"
|
||
output_connectors:
|
||
to_stage_1: connector_of_shared_memory
|
||
default_sampling_params:
|
||
temperature: 0.8
|
||
top_k: 30
|
||
top_p: 0.9
|
||
max_tokens: 2048
|
||
seed: 42
|
||
repetition_penalty: 1.0
|
||
|
||
- stage_id: 1
|
||
max_num_seqs: 1
|
||
gpu_memory_utilization: 0.1
|
||
enforce_eager: true
|
||
trust_remote_code: true
|
||
enable_prefix_caching: false
|
||
async_scheduling: false
|
||
max_num_batched_tokens: 16384
|
||
max_model_len: 16384
|
||
devices: "0"
|
||
input_connectors:
|
||
from_stage_0: connector_of_shared_memory
|
||
default_sampling_params:
|
||
temperature: 0.0
|
||
top_p: 1.0
|
||
top_k: -1
|
||
max_tokens: 65536
|
||
seed: 42
|
||
repetition_penalty: 1.0
|
||
|
||
platforms:
|
||
xpu:
|
||
stages:
|
||
# Verified on Intel Arc B60.
|
||
- stage_id: 0
|
||
gpu_memory_utilization: 0.8
|
||
max_model_len: 2048
|
||
max_num_batched_tokens: 2048
|
||
- stage_id: 1
|
||
max_model_len: 2048
|
||
max_num_batched_tokens: 2048
|