[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

Signed-off-by: Bill Nell <bnell@redhat.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-02-05 13:07:18 -05:00
parent 1ee95841bd
commit a57c8228ff
37 changed files with 132 additions and 109 deletions
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
@@ -924,4 +924,5 @@ class GPTQMarlinMoEMethod(FusedMoEMethodBase):
            workspace=layer.workspace,
            is_k_full=self.is_k_full,
            input_dtype=self.input_dtype,
+            inplace=not self.moe.disable_inplace,
        )