[Custom Ops] Add functional + out variant for scaled_fp4_quant (#34389)

Signed-off-by: tianrengao <terrygao87@gmail.com>
2026-03-16 15:51:46 -07:00
parent 7961486a9b
commit 3e6a1e1686
12 changed files with 213 additions and 44 deletions
--- a/tests/compile/passes/distributed/test_fusion_all_reduce.py
+++ b/tests/compile/passes/distributed/test_fusion_all_reduce.py
@@ -179,7 +179,7 @@ class TestAllReduceFusedAddRMSNormStaticQuantFP4Model(torch.nn.Module):
    def ops_in_model_before(self):
        return [
            torch.ops.vllm.all_reduce.default,
-            torch.ops._C.scaled_fp4_quant.default,
+            torch.ops._C.scaled_fp4_quant.out,
        ]