60 lines
1.5 KiB
YAML
60 lines
1.5 KiB
YAML
# MiniCPM-o 4.5 default deploy: single-GPU layout.
|
|
#
|
|
# Both stages are co-located on GPU 0:
|
|
# Stage 0 (thinker): multimodal understanding, ~80% mem.
|
|
# Stage 1 (talker) : MiniCPMTTS + in-process Token2Wav vocoder, ~10% mem
|
|
# (talker LM plus the vocoder that emits the waveform).
|
|
#
|
|
# Other GPU layouts: minicpmo_4_5_3gpu.yaml, minicpmo_4_5_8x4090.yaml.
|
|
async_chunk: false
|
|
|
|
trust_remote_code: true
|
|
enable_prefix_caching: false
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
max_num_seqs: 16
|
|
gpu_memory_utilization: 0.8
|
|
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
|
|
# Talker only consumes runtime_additional_information[0]; any value > 1
|
|
# makes concurrent requests share request-0's audio (mm_outputs fallback).
|
|
max_num_seqs: 1
|
|
gpu_memory_utilization: 0.1
|
|
enforce_eager: false
|
|
max_num_batched_tokens: 8192
|
|
devices: "0"
|
|
default_sampling_params:
|
|
temperature: 0.0
|
|
top_p: 1.0
|
|
top_k: -1
|
|
max_tokens: 1
|
|
seed: 42
|
|
detokenize: false
|
|
|
|
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
|