From e96dc673984593db5e27709591f22b8ae13e9ff7 Mon Sep 17 00:00:00 2001
From: Frank Liu <frankfliu2000@gmail.com>
Date: Fri, 1 Dec 2023 14:58:29 -0800
Subject: [PATCH] [docs] Adds option.max_output_size document (#1354)

---
 serving/docs/configurations_model.md | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/serving/docs/configurations_model.md b/serving/docs/configurations_model.md
index 394a98310..a844cda86 100644
--- a/serving/docs/configurations_model.md
+++ b/serving/docs/configurations_model.md
@@ -58,7 +58,9 @@ option.disablePerSessionThreads=true
 option.ortDevice=TensorRT/ROCM/CoreML
 
 # Python model options
-retry_threshold=10 # Mark model as failure after python process crashing 10 times
+# Mark model as failure after python process crashing 10 times
+retry_threshold=10
+
 option.pythonExecutable=python3
 option.entryPoint=deepspeed.py
 option.handler=hanlde
@@ -72,6 +74,9 @@ option.rolling_batch=auto
 option.max_rolling_batch_size=64
 option.paged_attention=false
 option.max_rolling_batch_prefill_tokens=1088
+
+# max output size in bytes, default to 60M
+option.max_output_size=67108864
 ```
 
 Most of the options can also be overriden by an environment variable with the `OPTION_` prefix and all caps.