From 8b7500ede9185a9d8ff6d7a595082325707ffa65 Mon Sep 17 00:00:00 2001
From: Pius Fung <pius@elastic.co>
Date: Tue, 17 Dec 2024 13:03:28 -0800
Subject: [PATCH] Update start-trained-model-deployment.asciidoc (#118887)

Updating with changes in https://github.com/elastic/elasticsearch/pull/115041
---
 .../apis/start-trained-model-deployment.asciidoc          | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/docs/reference/ml/trained-models/apis/start-trained-model-deployment.asciidoc b/docs/reference/ml/trained-models/apis/start-trained-model-deployment.asciidoc
index 6f7e2a4d9f988..bf9c4d14db290 100644
--- a/docs/reference/ml/trained-models/apis/start-trained-model-deployment.asciidoc
+++ b/docs/reference/ml/trained-models/apis/start-trained-model-deployment.asciidoc
@@ -138,8 +138,8 @@ normal priority deployments.
 Controls how many inference requests are allowed in the queue at a time.
 Every machine learning node in the cluster where the model can be allocated
 has a queue of this size; when the number of requests exceeds the total value,
-new requests are rejected with a 429 error. Defaults to 1024. Max allowed value
-is 1000000.
+new requests are rejected with a 429 error. Defaults to 10000. Max allowed value
+is 100000.
 
 `threads_per_allocation`::
 (Optional, integer)
@@ -173,7 +173,7 @@ The API returns the following results:
             "model_bytes": 265632637,
             "threads_per_allocation" : 1,
             "number_of_allocations" : 1,
-            "queue_capacity" : 1024,
+            "queue_capacity" : 10000,
             "priority": "normal"
         },
         "routing_table": {
@@ -229,4 +229,4 @@ POST _ml/trained_models/my_model/deployment/_start?deployment_id=my_model_for_se
   }
 }
 --------------------------------------------------
-// TEST[skip:TBD]
\ No newline at end of file
+// TEST[skip:TBD]