From e3657929977cf531cf9729f2f93baecdf9506547 Mon Sep 17 00:00:00 2001
From: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Date: Fri, 16 Oct 2026 01:28:59 -0400
Subject: [PATCH] [Dependency] Upgrade TokenSpeed MLA to 2.0.3 (#61689)

Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
---
 requirements/cuda.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements/cuda.txt b/requirements/cuda.txt
index a990dda387..e3d659545c 100644
--- a/requirements/cuda.txt
+++ b/requirements/cuda.txt
@@ -25,7 +25,7 @@ nvidia-cutlass-dsl[cu13]==4.8.0
 quack-kernels==0.6.5  # Required by MSA
 
 # Tokenspeed_MLA for faster mla with spec decode
-tokenspeed-mla==2.0.2; platform_system == "Linux"
+tokenspeed-mla==2.0.3; platform_system == "Linux"
 
 # Humming kernels for quantization gemm
 humming-kernels[cu13]==0.1.17