From b639327ad94b3aa16022ebea49f8e525660b736b Mon Sep 17 00:00:00 2001
From: Michael Goin <mgoin64@gmail.com>
Date: Sat, 12 Jul 2025 15:07:35 +0900
Subject: [PATCH] Revert "Use NVCC --compress-mode to reduce binary size by 30%
 #20694" (#20853)

Signed-off-by: mgoin <mgoin64@gmail.com>
---
 CMakeLists.txt | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 538f9adcb24ed..e59e912a99132 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -171,16 +171,6 @@ if(NVCC_THREADS AND VLLM_GPU_LANG STREQUAL "CUDA")
   list(APPEND VLLM_GPU_FLAGS "--threads=${NVCC_THREADS}")
 endif()
 
-#
-# Set nvcc fatbin compression.
-#
-if(VLLM_GPU_LANG STREQUAL "CUDA")
-  if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8)
-    list(APPEND VLLM_GPU_FLAGS "-Xfatbin" "-compress-all" "-compress-mode=size")
-  endif()
-endif()
-
-
 #
 # Use FetchContent for C++ dependencies that are compiled as part of vLLM's build process.
 # setup.py will override FETCHCONTENT_BASE_DIR to play nicely with sccache.