chore: upgrade flashinfer 0.4.0 (#11364)

2025-10-09 14:17:54 -07:00
parent 88bb627d0d
commit 44cb060785
5 changed files with 6 additions and 4 deletions
--- a/python/sglang/srt/layers/attention/flashinfer_mla_backend.py
+++ b/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,