From c61b29b9ce143e778fc717accd70e0bbabede720 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 28 Sep 2024 20:33:17 -0700
Subject: [PATCH] Simplify the warning when flash-attn fails to import

---
 modules/exllamav2.py    | 8 --------
 modules/exllamav2_hf.py | 8 --------
 2 files changed, 16 deletions(-)

diff --git a/modules/exllamav2.py b/modules/exllamav2.py
index 42b9ade1..0498c488 100644
--- a/modules/exllamav2.py
+++ b/modules/exllamav2.py
@@ -19,14 +19,6 @@ from modules.text_generation import get_max_prompt_length
 
 try:
     import flash_attn
-except ModuleNotFoundError:
-    logger.warning(
-        'You are running ExLlamaV2 without flash-attention. This will cause the VRAM usage '
-        'to be a lot higher than it could be.\n'
-        'Try installing flash-attention following the instructions here: '
-        'https://github.com/Dao-AILab/flash-attention#installation-and-features'
-    )
-    pass
 except Exception:
     logger.warning('Failed to load flash-attention due to the following error:\n')
     traceback.print_exc()
diff --git a/modules/exllamav2_hf.py b/modules/exllamav2_hf.py
index 96a89429..320a8d24 100644
--- a/modules/exllamav2_hf.py
+++ b/modules/exllamav2_hf.py
@@ -21,14 +21,6 @@ from modules.logging_colors import logger
 
 try:
     import flash_attn
-except ModuleNotFoundError:
-    logger.warning(
-        'You are running ExLlamaV2 without flash-attention. This will cause the VRAM usage '
-        'to be a lot higher than it could be.\n'
-        'Try installing flash-attention following the instructions here: '
-        'https://github.com/Dao-AILab/flash-attention#installation-and-features'
-    )
-    pass
 except Exception:
     logger.warning('Failed to load flash-attention due to the following error:\n')
     traceback.print_exc()