Fix CP unit test on A100 and L40s (#1211)

skip FP8 CP tests if hardware does not support FP8

Signed-off-by: Xiaowei Ren <[email protected]>

Author: xrennvidia

tests/pytorch/fused_attn/test_fused_attn_with_cp.py

@@ -112,6 +112,8 @@ def test_cp_with_fused_attention(dtype, model, qkv_format, cp_comm_type):
         pytest.skip("THD format is only supported on sm90+!")
     if cp_comm_type == "all_gather" and get_cudnn_version() < (9, 3, 0):
         pytest.skip("CP implementation with KV all-gather is only supported with cuDNN >= 9.3.0!")
+    if dtype == "fp8" and get_device_compute_capability() < (9, 0):
+        pytest.skip("FP8 attention is only supported on sm90+!")
 
     config = model_configs_fused_attn[model]
     if qkv_format == "thd" and config.num_heads != config.num_gqa_groups: