Files
vllm-omni/vllm_omni/deploy/minicpmo_4_5_duplex.yaml
T

43 lines
1.3 KiB
YAML

# MiniCPM-o 4.5 native duplex deployment.
#
# The registered minicpmo_4_5 pipeline owns the fixed
# Thinker -> Talker -> Code2Wav topology. This overlay changes session
# lifetime and bounds all three stages to two live duplex sessions.
base_config: minicpmo_4_5.yaml
pipeline: minicpmo_4_5
session_mode: duplex
active_stream_window: 1
duplex_session:
idle_ttl_s: 300
disconnect_grace_s: 30
reaper_interval_s: 5
resume_replay_ttl_s: 60
resume_replay_max_bytes_per_session: 8388608
max_pending_input_bytes_per_session: 16777216
max_pending_turns_per_session: 4
# Matches the configured Stage0/Stage1 sequence capacity below.
max_sessions: 2
completed_append_cache_size: 256
stages:
- stage_id: 0
max_num_seqs: 2
async_scheduling: false
- stage_id: 1
max_num_seqs: 2
async_scheduling: false
# Talker context is 4096 (tts_config.max_position_embeddings).
max_model_len: 4096
# Overlay only the knobs duplex changes. Codec temperature / top_k stay
# on the base YAML. Native duplex still ends each Talker request after
# one generate_chunk (26 samples, last is codec EOS) inside the model;
# YAML max_tokens is only the hard ceiling.
default_sampling_params:
max_tokens: 4096
min_tokens: 0
- stage_id: 2
max_num_seqs: 2
async_scheduling: false