Temporarily disable unit test of torch native attention backend (#2492)

9cd9dc83 · Lianmin Zheng · GitHub · 7a1aecb9 · 9cd9dc83
Unverified Commit 9cd9dc83 authored Dec 16, 2024 by Lianmin Zheng Committed by GitHub Dec 16, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

test/srt/run_suite.py test/srt/run_suite.py +2 -1

No files found.
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -34,7 +34,8 @@ suites = {
        "test_srt_endpoint.py",
        "test_torch_compile.py",
        "test_torch_compile_moe.py",
-        "test_torch_native_attention_backend.py",
+        # Temporarily disable this because it requires PyTorch >= 2.5
+        # "test_torch_native_attention_backend.py",
        "test_torchao.py",
        "test_triton_attention_kernels.py",
        "test_triton_attention_backend.py",