From 07821352fbbccefcd5d68d017f7d1f8bf5f1c671 Mon Sep 17 00:00:00 2001
From: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Date: Mon, 1 Dec 2025 12:59:09 -0800
Subject: [PATCH] Revert "Skip weight loading in deepgemm compilation" (#14241)

---
 python/sglang/compile_deep_gemm.py | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/python/sglang/compile_deep_gemm.py b/python/sglang/compile_deep_gemm.py
index 7e1e68301..11370acde 100644
--- a/python/sglang/compile_deep_gemm.py
+++ b/python/sglang/compile_deep_gemm.py
@@ -148,9 +148,6 @@ def refine_server_args(server_args: ServerArgs, compile_args: CompileArgs):
     server_args.enable_torch_compile = False
     print(f"Disable CUDA Graph and Torch Compile to save time...")
 
-    server_args.load_format = "dummy"
-    print(f"Set load format to dummy to save time...")
-
     # Set watchdog timeout to compile_args.timeout because compilation will take a long time
     server_args.watchdog_timeout = compile_args.timeout
     server_args.warmups = "compile-deep-gemm"