# 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. # # The default is the FAST profile (TTFP 712 ms -> 408 ms and realtime audio # delivery — one 80 ms packet per frame, median inter-chunk gap ~81 ms, # RTF ~1.01 on the bundled turn_taking fixture, 1x H100): the thinker runs # bf16 + CUDA graphs (inherited from the streaming base) and the talker's # Gemma3 backbone runs as a native vLLM model on PagedAttention, so the # duplex session length is unbounded (no StaticCache bucket cap) and the # per-frame talker cost drops below the vendored step. Every fast setting is # marked with a "PARITY:" comment here and in the streaming base; apply those # edits for the eager fp32 reference execution. # # Native-talker semantics: # * stage 1 sets max_num_batched_tokens: 64 so the speaker-prompt prefill # (hf_overrides.talker_init_len positions, embeddings precomputed — no # step-to-step feedback) runs as ONE chunked prefill at session start. # The per-frame code feedback IS strictly sequential, so the # thinker->talker producer ships at most one new timeline token per # chunk (drip; see thinker2talker_async_chunk) — at most one timeline # position is ever schedulable per engine step. # * the connector extra `native_talker: true` makes the thinker->talker # producer append one engine position PER NEW timeline token (engine # positions map 1:1 onto timeline steps). # * matching NeMo's realtime pipeline, the talker never sees the system # prompt (it conditions the thinker only); the duplex timeline is one # anchor PAD + the per-frame text tokens. # * classifier-free guidance is OFF by default (measured ASR-equivalent at # this checkpoint's guidance_scale=0.2); opt in via # hf_overrides.native_talker_guidance below (duplex pacing stays # realtime with it on). 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 # Startup warmup: run two silent frames through a throwaway session before # real clients are admitted, so one-time costs (kernel JIT, first # prefill/decode paths, codec caches) never land on the first user. warmup_frames: 2 async_chunk: true connectors: connector_of_shared_memory: name: SharedMemoryConnector extra: shm_threshold_bytes: 65536 codec_chunk_frames: 1 # PARITY: delete this line together with the stage-1 hf_overrides # below (the vendored talker drains chunks model-side and keeps the # 1-position-per-chunk default). native_talker: true 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 # PARITY: set enforce_eager: true, delete max_num_batched_tokens and the # hf_overrides block (and the connector's native_talker flag above) for # the vendored eager talker of the reference duplex deployment. enforce_eager: false max_num_batched_tokens: 64 hf_overrides: use_native_talker: true talker_init_len: 37 # The prewarmed placeholder prompt must cover the speaker-prompt # prefill positions (read by the orchestrator's async-chunk prewarm). async_chunk_prewarm_prompt_len: 37 # Classifier-free guidance: mirrors the stream on the vendored HF # backbone (captured StaticCache step) and blends per NeMo's # generate_step math (~+8.5 ms/frame, still realtime). Requires # gpu_memory_utilization ~0.18 on this stage. # native_talker_guidance: true - stage_id: 2 max_num_seqs: 1 async_scheduling: false