diff --git a/release-notes.d/unreleased/2123.md b/release-notes.d/unreleased/2123.md new file mode 100644 index 0000000000..990f671067 --- /dev/null +++ b/release-notes.d/unreleased/2123.md @@ -0,0 +1,7 @@ +--- +pr: 2123 +url: https://github.com/llm-d/llm-d-router/pull/2123 +author: LukeAVanDrie +date: 2026-07-23 +--- +Flow control queueing is now bounded by default: `defaultRequestTTL` defaults to 60s and per-band `maxRequests` defaults to 5000 when unset. For existing flow control users this is a behavior change: an explicit `defaultRequestTTL: "0s"` disables the TTL (requests then wait until client disconnect), and a band `maxRequests`/`maxBytes` of 0 is treated as unset and receives the default. To approximate the legacy fast-fail behavior for sheddable traffic, configure a small `defaultNegativePriorityBand.maxRequests`. Scale-to-zero deployments should raise `defaultRequestTTL` above the expected cold-start time.