diff --git a/docs/source/basic_tutorials/launcher.md b/docs/source/basic_tutorials/launcher.md
index bafe3669219..712b4fc43d8 100644
--- a/docs/source/basic_tutorials/launcher.md
+++ b/docs/source/basic_tutorials/launcher.md
@@ -354,6 +354,14 @@ Options:
           
           [env: NGROK_EDGE=]
 
+```
+## TOKENIZER_CONFIG_PATH
+```shell
+      --tokenizer-config-path <TOKENIZER_CONFIG_PATH>
+          The path to the tokenizer config file. This path is used to load the tokenizer configuration which may include a `chat_template`. If not provided, the default config will be used from the model hub
+          
+          [env: TOKENIZER_CONFIG_PATH=]
+
 ```
 ## ENV
 ```shell
diff --git a/launcher/src/main.rs b/launcher/src/main.rs
index 09657c91550..f0e45141157 100644
--- a/launcher/src/main.rs
+++ b/launcher/src/main.rs
@@ -368,6 +368,11 @@ struct Args {
     #[clap(long, env)]
     ngrok_edge: Option<String>,
 
+    /// The path to the tokenizer config file. This path is used to load the tokenizer configuration which may
+    /// include a `chat_template`. If not provided, the default config will be used from the model hub.
+    #[clap(long, env)]
+    tokenizer_config_path: Option<String>,
+
     /// Display a lot of information about your runtime environment
     #[clap(long, short, action)]
     env: bool,
@@ -1016,6 +1021,12 @@ fn spawn_webserver(
         args.model_id,
     ];
 
+    // Tokenizer config path
+    if let Some(ref tokenizer_config_path) = args.tokenizer_config_path {
+        router_args.push("--tokenizer-config-path".to_string());
+        router_args.push(tokenizer_config_path.to_string());
+    }
+
     // Model optional max batch total tokens
     if let Some(max_batch_total_tokens) = args.max_batch_total_tokens {
         router_args.push("--max-batch-total-tokens".to_string());