Files
LocalAI/core
Ettore Di Giacinto ec33f2334d fix(distributed): release staged request inputs
Ephemeral inputs remained on workers after inference completed. Release each exact key after synchronous and streaming calls, including partial staging failures.

Use a bounded cleanup context so caller cancellation cannot suppress release. Preserve caller requests and backend results when cleanup fails.

Assisted-by: Codex:gpt-6
2026-09-08 13:35:31 +00:00
..
2026-03-30 00:47:27 +02:00