e30c5ed386
Round 38 P1: R35e added the public_load_pending() check to the
route-side _raise_if_helper_advisor_busy, but the backend-side
_raise_if_helper_advisor_busy_for_diffusion (used by direct
DiffusionBackend.load_model callers AND called transitively from
the route via backend.load_model) never got the same parity
check. That left a window where:
* /api/training/start published the "training" pending marker
via the route helper
* a script/test calling DiffusionBackend.load_model() directly
passed the backend's helper-busy snapshot, never checked
public_load_pending(), and proceeded to destructive owner
teardown + GPU allocation while training was still pending.
Add the parity check with a kw-only `excluding` parameter on
public_load_pending so a route-wrapped backend call can ignore
the marker its own route already published (route publishes
"diffusion"; backend publishes the separate "diffusion-backend"
tag). load_model gains ignore_public_load_pending_workload to
thread the route's tag through; the diffusion route passes
"diffusion" so the backend's atomic check does not self-block
on the route's own publication.
Verified by smoke test: route-wrapped backend with excluding=
"diffusion" allowed during route's diffusion pending; direct
backend call refused with RuntimeError "Another GPU workload is
mid-handoff" when training is pending. 86 backend tests pass.
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| chat_templates.py | ||
| data_collators.py | ||
| dataset_utils.py | ||
| format_conversion.py | ||
| format_detection.py | ||
| llm_assist.py | ||
| model_mappings.py | ||
| raw_text.py | ||
| vlm_processing.py | ||