# Opt-in CUDA MRV2 for MOSS-TTS-Local-Transformer-v1.5. # Keep the base profile's batching, chunk geometry and V1 default. base_config: moss_tts_local.yaml model_runner: v2 platforms: cuda: stages: - stage_id: 0 # Bound prefill work so new prompts do not monopolize streaming decode. max_num_batched_tokens: 512 - stage_id: 1 compilation_config: # The codec owns CUDA Graph capture/replay. Skip Inductor compilation # of its stateful decoder; plain CUDA graphs remain enabled. mode: 0 # FULL works without Inductor; the default FULL_AND_PIECEWISE would # normalize to NONE and erase the codec's capture sizes. cudagraph_mode: FULL # Platform overrides replace compilation_config as a whole. cudagraph_capture_sizes: [1, 2, 4, 8, 16, 32, 64] cudagraph_num_of_warmups: 1 npu: model_runner: v1 xpu: model_runner: v1 rocm: model_runner: v1 musa: model_runner: v1