lhk229
07ba02fdde
CPU_WORKERS / GPU_CONCURRENCY were env-only. Add a `server:` config section (server.cpu_workers, server.gpu_concurrency) so a lane's concurrency lives in its yaml alongside device/precision, matching how model.device already works. Precedence mirrors BGFILTER_DEVICE: config is the default, the env var overrides per box. The pool + admission semaphore now build in lifespan (after the config loads) instead of at import, and PipelineManager reads gpu_concurrency from the settings. configs/gpu.yaml ships 8 / 2 (its target is the 32 GB GPU boxes) with an inline VRAM caveat: gpu_concurrency>1 must fit weights + N × forward, so keep it 1 on ≤16 GB cards. Verified on a 4080 SUPER: startup logs cpu_workers=8 gpu_concurrency=2 from gpu.yaml with no env set, request returns a valid RGBA. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
88 lines
2.8 KiB
YAML
88 lines
2.8 KiB
YAML
# GPU lane: CUDA + bf16 across all three models. Full pipeline (BiRefNet seg +
|
|
# ViTMatte + HR-matting cross-check). Foreground estimation auto-uses the CuPy GPU
|
|
# backend when cupy is installed (see foreground.use_gpu, default on). despill is
|
|
# off (it false-positives on subjects sharing the background hue).
|
|
screen_color: null
|
|
|
|
chroma:
|
|
# true = flat-colour background (default). false = non-flat/complex background
|
|
# mode: no colour key; segmentation alone drives the trimap (mode forced to
|
|
# "seg") and the colour-keyed stages are bypassed (auto-detect, hue split,
|
|
# chroma suppression, despill). The cross-check veto still runs if enabled,
|
|
# using its hue-free gate (cross_check.second_lo/hi). The service selects this
|
|
# per request via background_mode=flat|complex; this is only the base default.
|
|
enabled: true
|
|
|
|
model:
|
|
model_name: hustvl/vitmatte-base-composition-1k
|
|
device: cuda
|
|
matting_method: vitmatte
|
|
fallback_to_chroma_alpha: false
|
|
precision: bf16
|
|
attn_query_chunk: 2048
|
|
|
|
segmentation:
|
|
enabled: true
|
|
backend: birefnet
|
|
model_name: ZhengPeng7/BiRefNet
|
|
device: cuda
|
|
input_size: 1024
|
|
precision: bf16
|
|
|
|
trimap:
|
|
sure_bg_threshold: 0.92
|
|
sure_fg_threshold: 0.12
|
|
unknown_radius_ratio: 0.012
|
|
fg_safe_radius_ratio: 0.006
|
|
seg_core_threshold: 0.60
|
|
seg_loose_threshold: 0.08
|
|
mode: directional
|
|
seg_low: 0.15
|
|
bg_hue_proj_min: 4.0
|
|
seg_force_fg: 0.98
|
|
|
|
alpha_post:
|
|
chroma_suppress: true
|
|
chroma_suppress_bg_low: 0.35
|
|
chroma_suppress_bg_high: 0.80
|
|
chroma_suppress_strength: 1.0
|
|
suppress_raw_lo: 0.85
|
|
suppress_raw_hi: 0.98
|
|
|
|
cross_check:
|
|
enabled: true
|
|
model_name: ZhengPeng7/BiRefNet_HR-matting
|
|
input_size: 2048
|
|
reuse_as_seg: false
|
|
precision: bf16
|
|
proj_min: 3.0
|
|
l_min: 45.0
|
|
feather_sigma: 2.0
|
|
gate_lo: 0.70
|
|
gate_hi: 0.95
|
|
# Complex-background (non-flat) mode only: no hue-defined suspect zone, so the
|
|
# veto requires the second opinion itself to be confidently near-empty -- full
|
|
# strength at/below second_lo, fading to none at/above second_hi.
|
|
second_lo: 0.15
|
|
second_hi: 0.40
|
|
|
|
foreground:
|
|
enabled: true
|
|
method: ml
|
|
ml_regularization: 0.00001
|
|
|
|
despill:
|
|
enabled: false
|
|
|
|
server:
|
|
# Request concurrency (HTTP service only). cpu_workers = thread-pool size: >1 runs
|
|
# several requests at once, overlapping their CPU stages while the GPU forwards
|
|
# stay serialized -- keeps the GPU fed. gpu_concurrency = how many forwards may
|
|
# co-schedule on the SMs at once: 2 lifts GPU-bound throughput (batch-1 underfills
|
|
# the SMs) but roughly DOUBLES GPU activation memory.
|
|
# * On a >=24 GB card (e.g. 4080 SUPER 32 GB): gpu_concurrency: 2 peaks ~19 GB.
|
|
# * On a <=16 GB card: keep gpu_concurrency: 1 or it will OOM at 2048 cross-check.
|
|
# Env vars BGFILTER_CPU_WORKERS / BGFILTER_GPU_CONCURRENCY override these per box.
|
|
cpu_workers: 8
|
|
gpu_concurrency: 2
|