diff --git a/tests/pytorch/attention/test_attention.py b/tests/pytorch/attention/test_attention.py index bfd2cdf9fd..c877a29fe3 100644 --- a/tests/pytorch/attention/test_attention.py +++ b/tests/pytorch/attention/test_attention.py @@ -104,8 +104,10 @@ def reset_global_fp8_state(): ("2.8.3", True), ("2.8.3+local_version", True), ("2.8.3.post1", True), - ("2.8.4", False), - ("2.8.4+local_version", False), + ("2.8.4", True), + ("2.8.4+local_version", True), + ("2.8.5", False), + ("2.8.5+local_version", False), ("2.9.0", False), ), ) @@ -125,7 +127,7 @@ def test_flash_attention_supported_version_message(): _get_supported_versions( FlashAttentionUtils.version_required, FlashAttentionUtils.max_version ) - == ">= 2.1.1, < 2.8.4" + == ">= 2.1.1, < 2.8.5" ) diff --git a/transformer_engine/pytorch/attention/dot_product_attention/utils.py b/transformer_engine/pytorch/attention/dot_product_attention/utils.py index 645d9974e1..b987609a9d 100644 --- a/transformer_engine/pytorch/attention/dot_product_attention/utils.py +++ b/transformer_engine/pytorch/attention/dot_product_attention/utils.py @@ -122,7 +122,7 @@ class FlashAttentionUtils: version = PkgVersion("0") version_required = PkgVersion("2.1.1") version_required_blackwell = PkgVersion("2.7.3") - max_version = PkgVersion("2.8.4") + max_version = PkgVersion("2.8.5") v2_plus = False v2_1_plus = False v2_3_plus = False