From 8260dc00d8c24bb3f106739e3fdcd6568d5badb4 Mon Sep 17 00:00:00 2001
From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
Date: Wed, 10 Jan 2024 17:17:19 +0100
Subject: [PATCH] fix env var

---
 server/text_generation_server/models/flash_causal_lm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py
index e68a2100..21ed4f6c 100644
--- a/server/text_generation_server/models/flash_causal_lm.py
+++ b/server/text_generation_server/models/flash_causal_lm.py
@@ -777,7 +777,7 @@ class FlashCausalLM(Model):
             self.device,
         )
 
-        if os.getenv("ENABLE_CUDA_GRAPHS", "false") == "true":
+        if os.getenv("ENABLE_CUDA_GRAPHS", "False") == "True":
             try:
                 # Warmup cuda graphs for all power of twos until 64
                 for i in range(6):