From 807ea52aa959f1c462f6fc440b8f22967ae1dab6 Mon Sep 17 00:00:00 2001 From: kursad Date: Fri, 12 Jun 2026 15:23:35 +0300 Subject: [PATCH] docs(proxy): document general_settings.cancel_on_disconnect --- docs/proxy/config_settings.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/proxy/config_settings.md b/docs/proxy/config_settings.md index 17e144fc4..ac6189c57 100644 --- a/docs/proxy/config_settings.md +++ b/docs/proxy/config_settings.md @@ -261,6 +261,7 @@ router_settings: | custom_auth | string | Write your own custom authentication logic [Doc Custom Auth](./custom_auth) | | max_parallel_requests | integer | The max parallel requests allowed per deployment | | global_max_parallel_requests | integer | The max parallel requests allowed on the proxy overall | +| cancel_on_disconnect | boolean | If true, cancels the in-flight upstream LLM request (non-streaming) when the client disconnects, freeing backend capacity (e.g. a vLLM GPU slot). The cancelled request is logged as a 499 failure. Default `false` | | infer_model_from_keys | boolean | If true, infers the model from the provided keys | | background_health_checks | boolean | If true, enables background health checks. [Doc on health checks](health) | | health_check_interval | integer | The interval for health checks in seconds [Doc on health checks](health) |