From c99b4bec8fe786f9a41b604c6df865ecf008e323 Mon Sep 17 00:00:00 2001
From: Nidhin Jose <nidhin.jose@flex.ai>
Date: Wed, 23 Jul 2025 23:54:40 +0530
Subject: [PATCH] fix: --max-generated-tokens was not used in HTTP request,
 always defaulted to 1024.

Refs: NOTICKET
---
 src/flexbench/runners/base.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/flexbench/runners/base.py b/src/flexbench/runners/base.py
index c02977f..2edd42f 100644
--- a/src/flexbench/runners/base.py
+++ b/src/flexbench/runners/base.py
@@ -95,7 +95,7 @@ def _make_api_request(
                 json={
                     "model": self.config.remote_model_path,
                     "prompt": inputs,
-                    "max_tokens": getattr(self, "max_tokens", 1024),
+                    "max_tokens": self.config.max_generated_tokens,
                     "temperature": 0,
                     "stream": stream,
                     "min_tokens": 1,