65 lines
1.9 KiB
YAML
65 lines
1.9 KiB
YAML
# MOSS-TTS Local Transformer v1.5: both stages on one H200.
|
|
# Select one free physical GPU with CUDA_VISIBLE_DEVICES; devices below are logical.
|
|
# Capacity and graph capture require more than 80 GiB of GPU memory.
|
|
async_chunk: true
|
|
|
|
connectors:
|
|
shm:
|
|
name: SharedMemoryConnector
|
|
extra:
|
|
connector_get_sleep_s: 0.005
|
|
connector_get_max_wait_first_chunk: 1000
|
|
connector_get_max_wait: 300
|
|
initial_codec_chunk_frames: 1
|
|
codec_chunk_frames: 15
|
|
codec_left_context_frames: 0
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_seqs: 256
|
|
gpu_memory_utilization: 0.60
|
|
kv_cache_memory_bytes: 34359738368 # 32 GiB; leave room for codec state and graphs.
|
|
enable_prefix_caching: false
|
|
async_scheduling: true
|
|
max_num_batched_tokens: 65536
|
|
max_model_len: 4096
|
|
devices: "0"
|
|
compilation_config:
|
|
# Capture mixed prefill/decode batches by total scheduled tokens.
|
|
cudagraph_capture_sizes: [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 160, 192, 224, 256, 320, 384, 448, 512]
|
|
max_cudagraph_capture_size: 512
|
|
output_connectors:
|
|
to_stage_1: shm
|
|
default_sampling_params:
|
|
temperature: 1.7
|
|
top_p: 0.8
|
|
top_k: 25
|
|
max_tokens: 4096
|
|
seed: 42
|
|
repetition_penalty: 1.0
|
|
|
|
- stage_id: 1
|
|
max_num_seqs: 256
|
|
gpu_memory_utilization: 0.30
|
|
enforce_eager: false
|
|
enable_prefix_caching: false
|
|
async_scheduling: true
|
|
compilation_config:
|
|
# Codec execution-batch buckets; frame counts come from the connector.
|
|
cudagraph_capture_sizes: [1, 2, 4, 8, 16, 32, 64, 128, 160, 192, 256]
|
|
cudagraph_num_of_warmups: 1
|
|
max_num_batched_tokens: 65536
|
|
max_model_len: 65536
|
|
devices: "0"
|
|
hf_overrides:
|
|
codec_attention_backend: triton
|
|
input_connectors:
|
|
from_stage_0: shm
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 65536
|
|
seed: 42
|
|
repetition_penalty: 1.0
|