nit: update SM120 comment to include attention kernels

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: blake-snc

flashinfer/aot.py

@@ -531,7 +531,7 @@ def gen_all_modules(
         if has_sm121:
             jit_specs.append(gen_fp4_quantization_sm121_module())
         if has_sm120 or has_sm121:
-            # SM120 and SM121 share the same CUTLASS kernels for fused MOE and GEMM.
+            # SM120 and SM121 share the same kernels for fused MOE, GEMM, and attention.
             # The SM120 module generators use supported_major_versions=[12] which
             # compiles for all SM12x targets.
             jit_specs.append(gen_cutlass_fused_moe_sm120_module())