aa5364f705
Signed-off-by: y_null <y_null@qq.com> Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com> Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
89 lines
2.2 KiB
YAML
89 lines
2.2 KiB
YAML
# MiniCPM-o 4.5 two-GPU continuous-batching layout.
|
|
#
|
|
# Thinker owns GPU 0. Talker and Code2Wav share GPU 1, keeping text decoding
|
|
# isolated from codec/vocoder contention while preserving stage-2 batching.
|
|
pipeline: minicpmo_4_5
|
|
async_chunk: true
|
|
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
|
|
connectors:
|
|
connector_of_shared_memory:
|
|
name: SharedMemoryConnector
|
|
extra:
|
|
connector_get_sleep_s: 0.01
|
|
connector_get_max_wait_first_chunk: 3000
|
|
connector_get_max_wait: 300
|
|
codec_chunk_frames: 25
|
|
codec_left_context_frames: 3
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_seqs: 4
|
|
gpu_memory_utilization: 0.9
|
|
enforce_eager: false
|
|
tensor_parallel_size: 1
|
|
max_num_batched_tokens: 16384
|
|
devices: "0"
|
|
limit_mm_per_prompt:
|
|
video: 1
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 2048
|
|
seed: 42
|
|
detokenize: true
|
|
repetition_penalty: 1.1
|
|
|
|
- stage_id: 1
|
|
max_num_seqs: 4
|
|
gpu_memory_utilization: 0.55
|
|
enforce_eager: false
|
|
max_num_batched_tokens: 8192
|
|
devices: "1"
|
|
output_connectors:
|
|
to_stage_2: connector_of_shared_memory
|
|
# Codec sampling is model-owned by the checkpoint's tts_config (defaults:
|
|
# T=0.8, top-k=25, top-p=0.85, repetition penalty=1.05, seed=42).
|
|
# These parameters only govern vLLM's binary continue/stop token.
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
min_tokens: 50
|
|
max_tokens: 2048
|
|
stop_token_ids: [1]
|
|
seed: 42
|
|
detokenize: false
|
|
|
|
- stage_id: 2
|
|
max_num_seqs: 4
|
|
gpu_memory_utilization: 0.35
|
|
enforce_eager: true
|
|
enable_chunked_prefill: false
|
|
max_num_batched_tokens: 65536
|
|
max_model_len: 65536
|
|
devices: "1"
|
|
input_connectors:
|
|
from_stage_1: connector_of_shared_memory
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 65536
|
|
detokenize: true
|
|
|
|
platforms:
|
|
npu:
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_batched_tokens: 8192
|
|
compilation_config:
|
|
cudagraph_mode: PIECEWISE
|
|
- stage_id: 1
|
|
max_num_batched_tokens: 8192
|
|
compilation_config:
|
|
cudagraph_mode: PIECEWISE
|