# Dynin-Omni deploy for e2e smoke tests (3-stage, one GPU).
#
# Topology is frozen in models/dynin_omni/pipeline.py; ``pipeline: dynin_omni``
# pins it explicitly so this CI YAML resolves regardless of model_type
# auto-detection. Differs from the default deploy only in reduced GPU memory
# and a smaller max_num_batched_tokens so the pipeline fits L4-class CI GPUs.
pipeline: dynin_omni
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: 4096
    enforce_eager: true
    async_scheduling: false

  - stage_id: 1
    devices: "0"
    max_num_seqs: 1
    gpu_memory_utilization: 0.2
    max_num_batched_tokens: 4096
    enforce_eager: true
    async_scheduling: false

  - stage_id: 2
    devices: "0"
    max_num_seqs: 1
    gpu_memory_utilization: 0.2
    max_num_batched_tokens: 4096
    enforce_eager: true
    async_scheduling: false