[CI/Build] Split up models tests (#10069)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2024-11-10 03:39:14 +08:00
parent b09895a618
commit 51c2e1fcef
21 changed files with 115 additions and 129 deletions
--- a/tests/models/decoder_only/language/test_fp8.py
+++ b/tests/models/decoder_only/language/test_fp8.py
@@ -15,6 +15,7 @@ from ...utils import check_logprobs_close
 os.environ["TOKENIZERS_PARALLELISM"] = "true"


+@pytest.mark.quant_model
@pytest.mark.skipif(not is_quant_method_supported("fp8"),
                    reason="fp8 is not supported on this GPU type.")
@pytest.mark.parametrize(