bvandeusen
6d7b17b0b5
The new per-job workload (3 detectors + several SigLIP embeds) is far more GPU-bound than the old I/O-bound CCIP pass, so the right worker count shifted and is hard to guess. Add an Auto mode (default ON) that finds it: - _control_loop samples jobs/sec + GPU util/VRAM every ~6s and hill-climbs the target: grow while throughput keeps improving and VRAM stays under budget, revert a step that doesn't help, back off under memory pressure (VRAM >= 90%), then settle and periodically re-probe (the GPU/IO balance shifts over a run). - A manual concurrency set is an override → leaves Auto; an "Auto" toggle in the control UI re-enables it. status() reports `auto`; the dial reflects the auto-chosen count (read-only) while Auto is on. - AUTO_SCALE env (default on) + compose doc. Agent py-compiled (outside CI). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
57 lines
3.1 KiB
Python
57 lines
3.1 KiB
Python
"""Agent config, all from env (the control container is configured at run)."""
|
|
import os
|
|
from dataclasses import dataclass
|
|
|
|
|
|
@dataclass
|
|
class Config:
|
|
fc_url: str # base URL of the FabledCurator web service
|
|
token: str # the bearer token from Settings → Tagging → GPU agent
|
|
agent_id: str # identifies this agent's leases
|
|
batch_size: int # jobs a worker leases per round
|
|
concurrency: int # INITIAL parallel workers (tunable live from the UI)
|
|
ccip_model: str # imgutils CCIP model name ("" → imgutils default)
|
|
detector_level: str # imgutils person-detector level: n|s|m|x
|
|
poll_idle_seconds: float # wait between empty leases
|
|
embed_dtype: str # torch dtype for the crop embedder: float16|float32
|
|
embed_model_override: str # force a SigLIP-family model ("" → use the one
|
|
# the server announces in the lease)
|
|
auto_start: bool # start the worker pool on boot (so a container restart
|
|
# resumes processing without anyone clicking Start)
|
|
auto_scale: bool # autoscale the worker count (throughput hill-climb)
|
|
# Crop PROPOSERS (extra YOLO detectors that say where to crop). Each weight
|
|
# spec is an ultralytics name | http(s) URL | "hf_repo::file" ("" = off).
|
|
person_weights: str # general COCO person detector (Western/realistic figs)
|
|
person_conf: float
|
|
anatomy_weights: str # booru_yolo anime/furry/NSFW components
|
|
anatomy_conf: float
|
|
panel_weights: str # comic-panel detector
|
|
panel_conf: float
|
|
max_components: int # cap anatomy component crops per frame
|
|
max_panels: int # cap panel crops per frame
|
|
|
|
@classmethod
|
|
def from_env(cls) -> "Config":
|
|
return cls(
|
|
fc_url=os.environ.get("FC_URL", "http://localhost:8000").rstrip("/"),
|
|
token=os.environ.get("FC_TOKEN", ""),
|
|
agent_id=os.environ.get("AGENT_ID", "desktop-agent"),
|
|
batch_size=int(os.environ.get("BATCH_SIZE", "4")),
|
|
concurrency=int(os.environ.get("CONCURRENCY", "1")),
|
|
ccip_model=os.environ.get("CCIP_MODEL", ""),
|
|
detector_level=os.environ.get("DETECTOR_LEVEL", "m"),
|
|
poll_idle_seconds=float(os.environ.get("POLL_IDLE_SECONDS", "10")),
|
|
embed_dtype=os.environ.get("SIGLIP_DTYPE", "float16"),
|
|
embed_model_override=os.environ.get("EMBED_MODEL_NAME", ""),
|
|
auto_start=os.environ.get("AUTO_START", "").lower() in ("1", "true", "yes"),
|
|
auto_scale=os.environ.get("AUTO_SCALE", "true").lower() in ("1", "true", "yes"),
|
|
person_weights=os.environ.get("PERSON_WEIGHTS", "yolo11n.pt"),
|
|
person_conf=float(os.environ.get("PERSON_CONF", "0.35")),
|
|
anatomy_weights=os.environ.get("ANATOMY_WEIGHTS", ""),
|
|
anatomy_conf=float(os.environ.get("ANATOMY_CONF", "0.30")),
|
|
panel_weights=os.environ.get("PANEL_WEIGHTS", ""),
|
|
panel_conf=float(os.environ.get("PANEL_CONF", "0.30")),
|
|
max_components=int(os.environ.get("MAX_COMPONENTS", "8")),
|
|
max_panels=int(os.environ.get("MAX_PANELS", "8")),
|
|
)
|