Files
vllm-omni/vllm_omni/deploy/minicpmo_4_5_duplex.yaml
T
05b794f29b [Full Duplex] Feat: Support Full-Duplex realtime runtime & add MiniCPM-o 4.5 demo (#3907)
Signed-off-by: Sy03 <1370724210@qq.com>
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: StormMelody <22371184@zju.edu.cn>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
2026-07-23 16:45:18 +08:00

37 lines
1.1 KiB
YAML

# MiniCPM-o 4.5 native duplex deployment.
#
# The registered minicpmo_4_5 pipeline owns the fixed Stage0 -> Stage1
# topology and llm2tts bridge. This overlay only changes session lifetime and
# the Stage1 token budget needed to drain streaming audio segments.
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
# The streaming talker advances Python-owned per-request generators on
# every step, so only fixed-topology model regions are graph-capturable.
compilation_config:
cudagraph_mode: PIECEWISE
default_sampling_params:
max_tokens: 4096
stop_token_ids: [151645]