Support nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8/NVFP4 (#11866)

2025-10-23 12:29:02 +03:00
parent 36a4cad7b0
commit d6fee73d1f
10 changed files with 207 additions and 127 deletions
--- a/test/srt/layers/attention/mamba/test_causal_conv1d.py
+++ b/test/srt/layers/attention/mamba/test_causal_conv1d.py
@@ -373,3 +373,7 @@ def test_causal_conv1d_varlen(
    )
    unpadded_out = out[:, : out_ref_tensor.shape[-1]]
    assert torch.allclose(unpadded_out, out_ref_tensor, rtol=rtol, atol=atol)
+
+
+if __name__ == "__main__":
+    pytest.main([__file__])