38 lines
1.1 KiB
YAML
38 lines
1.1 KiB
YAML
|
# Dynin-Omni 3-stage deploy: token2text → token2image → token2audio.
|
||
|
|
#
|
||
|
|
# Topology (stages, processor functions, model_arch) is frozen in
|
||
|
|
# vllm_omni/model_executor/models/dynin_omni/pipeline.py. This file carries
|
||
|
|
# only the deploy-time knobs (devices, GPU memory, batched tokens).
|
||
|
|
#
|
||
|
|
# async_chunk=false: dynin hands the full token payload across stages through
|
||
|
|
# the worker-connector data plane (``*_full_payload`` producers), not chunked
|
||
|
|
# streaming. Pipeline-wide ``trust_remote_code`` is required by the custom
|
||
|
|
# Dynin HF modeling code.
|
||
|
|
async_chunk: false
|
||
|
|
trust_remote_code: true
|
||
|
|
enable_prefix_caching: false
|
||
|
|
|
||
|
|
stages:
|
||
|
|
- stage_id: 0
|
||
|
|
devices: "0"
|
||
|
|
max_num_seqs: 1
|
||
|
|
gpu_memory_utilization: 0.5
|
||
|
|
max_num_batched_tokens: 32768
|
||
|
|
enforce_eager: true
|
||
|
|
async_scheduling: false
|
||
|
|
|
||
|
|
- stage_id: 1
|
||
|
|
devices: "0"
|
||
|
|
max_num_seqs: 1
|
||
|
|
gpu_memory_utilization: 0.1
|
||
|
|
max_num_batched_tokens: 32768
|
||
|
|
enforce_eager: true
|
||
|
|
async_scheduling: false
|
||
|
|
|
||
|
|
- stage_id: 2
|
||
|
|
devices: "0"
|
||
|
|
max_num_seqs: 1
|
||
|
|
gpu_memory_utilization: 0.1
|
||
|
|
max_num_batched_tokens: 32768
|
||
|
|
enforce_eager: true
|
||
|
|
async_scheduling: false
|