diff --git a/setup.py b/setup.py
index 53c460d2c5b8..08d29f8412d2 100644
--- a/setup.py
+++ b/setup.py
@@ -715,7 +715,7 @@ def _read_requirements(filename: str) -> list[str]:
         ],  # Required for audio processing
         "video": [],  # Kept for backwards compatibility
         # FlashInfer should be updated together with the Dockerfile
-        "flashinfer": ["flashinfer-python==0.3.1"],
+        "flashinfer": ["flashinfer-python==0.4.0rc4"],
         # Optional deps for AMD FP4 quantization support
         "petit-kernel": ["petit-kernel"],
     },