From 538bc5b8ab116b8bc97dfc9cf7ce45d5203b9fa8 Mon Sep 17 00:00:00 2001
From: "kevin.li" <kevin.li@modal.com>
Date: Wed, 30 Sep 2026 10:33:33 +0000
Subject: [PATCH] Target 16 concurrent inputs per execute_sample container

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 src/spindle/providers/modal/app.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/spindle/providers/modal/app.py b/src/spindle/providers/modal/app.py
index 010a694..59dbd91 100644
--- a/src/spindle/providers/modal/app.py
+++ b/src/spindle/providers/modal/app.py
@@ -267,7 +267,7 @@ async def _ready_lora_pool(spec: LoraPoolSpec) -> str:
     retries=2,
     secrets=[proxy_secret, modal.Secret.from_name(API_SECRET_NAME)],
 )
-@modal.concurrent(max_inputs=128)
+@modal.concurrent(max_inputs=128, target_inputs=16)
 async def execute_sample(task: dict) -> dict:
     stats: dict = {}
     with sample_trace(task, stats):