Zexi Li 3413845e96 feat(llm): backfill orphan LLM instances into deployments on init (#25079) ...

On service startup, find LLM instances without llm_deployment_id and
create a matching SLLMDeployment, then link the instance. Idempotent
across restarts; skipped on slave nodes.

2026-06-29 11:26:16 +08:00

..

drivers

Automated cherry pick of #25074: feat(llm): tool call defaults & auto gpu ultilization (#25075)

2026-06-26 10:15:55 +08:00

models

feat(llm): backfill orphan LLM instances into deployments on init (#25079)

2026-06-29 11:26:16 +08:00

options

feat(llm): add community images catalog API (#25030)

2026-06-15 17:26:25 +08:00

service

Automated cherry pick of #25016: Feature/http get+llm probe (#25045)

2026-06-23 19:40:46 +08:00

tasks

feat(llm): async instant model delete and improve import status tracking (#25072)

2026-06-25 19:52:28 +08:00

utils

feat(llm,scheduler): vram calculation (#24884)

2026-05-25 16:27:20 +08:00