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

This commit is contained in:
Netanel Haber
2025-10-23 12:29:02 +03:00
committed by GitHub
parent 36a4cad7b0
commit d6fee73d1f
10 changed files with 207 additions and 127 deletions

View File

@@ -1,5 +1,6 @@
# Adapted from https://github.com/vllm-project/vllm/blob/2c58742dff8613a3bd7496f2008ce927e18d38d1/tests/kernels/mamba/test_mamba_mixer2.py
from unittest.mock import patch
import pytest
@@ -136,3 +137,7 @@ def mixer2_gated_norm_tensor_parallel(
atol=5e-3,
rtol=1e-3,
)
if __name__ == "__main__":
pytest.main([__file__])