fix(mxfp4): return is_monolithic=False when LoRA is enabled for Triton backend (#35382)

Signed-off-by: Seungho Yoon <yoonsnowdev@gmail.com>
2026-03-01 23:59:30 +09:00
parent 59d7af9c6c
commit 5a435507d8
1 changed files with 2 additions and 0 deletions
--- a/vllm/model_executor/layers/quantization/mxfp4.py
+++ b/vllm/model_executor/layers/quantization/mxfp4.py
@@ -1001,6 +1001,8 @@ class Mxfp4MoEMethod(FusedMoEMethodBase):

    @property
    def is_monolithic(self) -> bool:
+        if self.moe.is_lora_enabled:
+            return False
        return (
            self.mxfp4_backend == Mxfp4Backend.SM100_FI_MXFP4_MXFP8_TRTLLM
            or self.mxfp4_backend == Mxfp4Backend.SM100_FI_MXFP4_BF16