chore: upgrade flashinfer 0.4.0 (#11364)

python/sglang/srt/entrypoints/engine.py

@@ -703,7 +703,7 @@ def _set_envs_and_config(server_args: ServerArgs):
     if server_args.attention_backend == "flashinfer":
         assert_pkg_version(
             "flashinfer_python",
-            "0.4.0rc3",
+            "0.4.0",
             "Please uninstall the old version and "
             "reinstall the latest version by following the instructions "
             "at https://docs.flashinfer.ai/installation.html.",

python/sglang/srt/layers/attention/flashinfer_mla_backend.py

@@ -1060,7 +1060,7 @@ def fast_mla_decode_plan(
 
     try:
         # Standard version with just the required arguments (no use_profiler)
-        self._cached_module.plan.default(
+        self._cached_module.plan(
             self._float_workspace_buffer,
             self._int_workspace_buffer,
             self._pin_memory_int_workspace_buffer,