From 80c23bdd3879ecf41e2f74011141a590e90132d2 Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Fri, 26 Apr 2024 19:16:39 +0200
Subject: [PATCH] Changing the waiting_served_ratio default (stack more
 aggressively by default).

---
 launcher/src/main.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/launcher/src/main.rs b/launcher/src/main.rs
index f264e000..28226fb4 100644
--- a/launcher/src/main.rs
+++ b/launcher/src/main.rs
@@ -251,7 +251,7 @@ struct Args {
     ///
     /// This setting is only applied if there is room in the batch
     /// as defined by `max_batch_total_tokens`.
-    #[clap(default_value = "1.2", long, env)]
+    #[clap(default_value = "0.3", long, env)]
     waiting_served_ratio: f32,
 
     /// Limits the number of tokens for the prefill operation.