[AMD] Update test_aiter_allgather_amd.py data types alignment between benchmark aiter and custom all-reduce kernel (#27815)

Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com> Co-authored-by: Hubert Lu <55214931+hubertlu-tw@users.noreply.github.com>
2026-06-17 00:48:15 -07:00
parent d0e974f40b
commit 7256ee9871
1 changed files with 0 additions and 7 deletions
@@ -35,13 +35,6 @@ class TestAiterAllGatherAmd(unittest.TestCase):
            "float32",
            "float16",
            "bfloat16",
-            "uint64_t",
-            "int64_t",
-            "uint32_t",
-            "int32_t",
-            "int16_t",
-            "uint8_t",
-            "int8_t",
        ]
        # Keep the CI matrix compact: one small metadata shape and one
        # medium aligned 2-D shape exercise both naive and vectorized kernels.