44 lines
1.6 KiB
YAML
44 lines
1.6 KiB
YAML
# CUDA system profile for MOSS-TTS-Local-Transformer-v1.5.
|
|
# Selected automatically with at least 140 GiB GPU memory and MPS available.
|
|
# Requires H200-class memory and nvidia-cuda-mps-control on PATH.
|
|
# Adds prefix caching, Triton backbone attention and faster codec dispatch;
|
|
# keeps the original Local depth projection and native Torch sampler.
|
|
# The throughput baseline remains moss_tts_local_mrv2_high_concurrency.yaml.
|
|
base_config: moss_tts_local_mrv2_high_concurrency.yaml
|
|
model_runner: v1
|
|
|
|
connectors:
|
|
shm:
|
|
extra:
|
|
codec_first_chunk_fast_path: 1
|
|
# Keep the fast first chunk for low load; coalesce crowded streams.
|
|
codec_first_chunk_max_active_streams: 32
|
|
generation_min_batch_size: 16
|
|
generation_max_wait_ms: 6
|
|
|
|
platforms:
|
|
cuda:
|
|
model_runner: v2
|
|
cuda_mps: true
|
|
stages:
|
|
- stage_id: 0
|
|
hf_overrides:
|
|
mrv2_gpu_slot_state: true
|
|
mrv2_batch_prefill: true
|
|
mrv2_direct_tokens: true
|
|
# Compile the native Torch sampler; explicit generators keep its fallback.
|
|
local_compile_audio_sampler: true
|
|
enable_prefix_caching: true
|
|
attention_config:
|
|
backend: TRITON_ATTN
|
|
- stage_id: 1
|
|
compilation_config:
|
|
mode: 3
|
|
backend: inductor
|
|
cudagraph_mode: FULL
|
|
cudagraph_capture_sizes: [1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 14, 16, 20, 24, 28, 32, 40, 48, 56, 64, 80, 96, 112, 128]
|
|
cudagraph_num_of_warmups: 1
|
|
inductor_compile_config:
|
|
combo_kernels: false
|
|
benchmark_combo_kernel: false
|