vh
888ba6a714
Host service (runs as llmuser, owns /opt/fluxgym + GPU access) that runs
sd-scripts SDXL LoRA training on demand for arbo — the infra-ops half of the
in-arbo LoRA training Phase 1 ownership split (vh/arbo
docs/contracts/in-arbo-lora-training-phase1.contract.md §4.1/§2).
- Fixed-invocation only (INV-T7): bounded params -> one sd-scripts command
shape; every param range/allowlist/path-containment checked before spawn;
bad request = 422, never a silent downgrade. 14 unit tests green.
- Thin supervisor: never imports torch; subprocesses the fluxgym venv's
accelerate. 1-job-at-a-time (arbo lease is the serializer, 409 is backstop).
Durable job records + boot reconciliation (§4.3).
- API: POST /train, GET /train/{id}[/log], POST /train/{id}/cancel,
GET /gpu-status (per-device VRAM + tts_on_3090 co-OOM signal), GET /healthz.
- Wire-shape (§7 resolved with comfy-dev): shared /worktank/arbo/train handoff
(group arbotrain, setgid 2770); worker binds 0.0.0.0:8203, arbo reaches via
host.docker.internal:host-gateway (reachability proven on 172.20.0.1:8203);
device-aware TTS steering via /gpu-status.
Deployed to irv-ml1 via playbooks/deploy-lora-training-worker.yaml (elway,
idempotent); systemd unit active; /healthz + /gpu-status verified live.
27 lines
630 B
TOML
27 lines
630 B
TOML
[project]
|
|
name = "lora-training-worker"
|
|
version = "0.1.0"
|
|
description = "Host service that runs sd-scripts LoRA training on demand for arbo (in-arbo LoRA training Phase 1, contract §4.1/§2). Fixed-invocation only (INV-T7)."
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"fastapi>=0.115",
|
|
"uvicorn[standard]>=0.34",
|
|
"pydantic>=2.9",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
test = [
|
|
"pytest>=8.0",
|
|
"httpx>=0.27", # fastapi TestClient
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["worker"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|