# Nemotron VoiceChat native Full-Duplex deployment. # # One scheduler segment consumes one 1280-sample (80 ms) microphone frame. # Stage 0 remains one resumable request, so its NemotronH KV/Mamba state is # preserved between frame appends. Stage 1 and the codec overlap per frame. base_config: nemotron_labs_voicechat_streaming.yaml pipeline: nemotron_voicechat 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 max_sessions: 1 completed_append_cache_size: 256 async_chunk: true connectors: connector_of_shared_memory: name: SharedMemoryConnector extra: shm_threshold_bytes: 65536 codec_chunk_frames: 1 stages: - stage_id: 0 max_num_seqs: 1 async_scheduling: false default_sampling_params: temperature: 0.0 max_tokens: 1 ignore_eos: true seed: 0 - stage_id: 1 max_num_seqs: 1 async_scheduling: false - stage_id: 2 max_num_seqs: 1 async_scheduling: false