[Bugfix] Fix fp8 tests for triton_unified_attention for Triton 3.3 (#18013)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

tests/kernels/attention/test_triton_unified_attention.py

@@ -99,6 +99,9 @@ def test_triton_unified_attn(
 ) -> None:
     torch.set_default_device("cuda")
 
+    if q_dtype is not None and q_dtype.itemsize < 2 and block_size < 32:
+        pytest.skip("block size must be at least 32 for fp8")
+
     current_platform.seed_everything(0)
     num_seqs = len(seq_lens)
     query_lens = [x[0] for x in seq_lens]