# Urgent CPU-only lane: fp32, birefnet segmentation, NO cross-check, NO anime-seg.
#
# This is the lightest production path: base ViTMatte + one BiRefNet@1024, ~14-15s
# per 1.5 MP image on CPU. It needs ONLY these two weights provisioned --
# BiRefNet_HR-matting (cross-check) and anime-seg are never loaded.
#
# Tuned for an 8 GB box (~7 GB for the service). Measured peak working set:
#   2048x1152 (2.4 MP) ~5.6 GB | 2048x2048 (4.2 MP) ~7.1 GB.
# The 2048x2048 peak is a floor set by ViTMatte's own dense compute, not the
# attention (shrinking the chunk below 512 does not lower it further). Set
# MemoryMax=8G with a hard 4 MP input cap (BGFILTER_MAX_IMAGE_PIXELS default),
# or cap inputs tighter if you need more headroom.
#
# Anything omitted here inherits the built-in defaults (identical to default.yaml).

model:
  device: cpu
  precision: fp32          # fp32 only: this lane targets non-bf16 CPUs
  # Query chunk of 512 (vs the 2048 default) trims ViTMatte's attention transient
  # ~0.9 GB at 2048x2048 (8.0 -> 7.1 GB) for ~1 s more compute; 256 gives nothing
  # more. Exact/bitwise-identical output -- purely a memory-vs-speed knob.
  attn_query_chunk: 512

segmentation:
  enabled: true
  backend: birefnet        # the only backend this lane uses
  device: cpu
  precision: fp32

cross_check:
  enabled: false           # no second-opinion HR-matting pass (the big cost/mem sink)
  lock: true               # ignore per-request cross_check=on so a request can't
                           # force the HR-matting load and OOM this low-memory lane