Quantization: support FP4 quantized models on AMD CDNA2/CDNA3 GPUs (#22527)

Signed-off-by: feng <fengli1702@gmail.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-08-23 10:53:21 +08:00
parent f6818a92cb
commit fa78de9dc3
8 changed files with 451 additions and 5 deletions
--- a/setup.py
+++ b/setup.py
@@ -695,6 +695,8 @@ setup(
        "video": [],  # Kept for backwards compatibility
        # FlashInfer should be updated together with the Dockerfile
        "flashinfer": ["flashinfer-python==0.2.12"],
+        # Optional deps for AMD FP4 quantization support
+        "petit-kernel": ["petit-kernel"],
    },
    cmdclass=cmdclass,
    package_data=package_data,