lhk229
38a0dc34cc
Urgent lightweight production profile for a CPU-only fp32 server: base ViTMatte + one BiRefNet@1024, cross-check disabled. Provisions only those two weights (no BiRefNet_HR-matting, no anime-seg) and returns to the ~14-15s/image baseline. Run with BGFILTER_CONFIG=configs/cpu-fast.yaml. Verified end-to-end: loads exactly 2 models, cross_check resolves off, service preloads the primary segmenter and not the cross-checker. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
21 lines
715 B
YAML
21 lines
715 B
YAML
# 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.
|
|
#
|
|
# 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
|
|
|
|
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)
|