From a5ccc85c8c98115981a39b010b36f255e6446e77 Mon Sep 17 00:00:00 2001 From: Samu Tamminen Date: Mon, 16 Feb 2026 11:32:30 +0200 Subject: [PATCH] [Bugfix] Fix Dynamo unexpected keyword argument (#34320) Signed-off-by: Samu Tamminen Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> --- vllm/model_executor/layers/quantization/input_quant_fp8.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/vllm/model_executor/layers/quantization/input_quant_fp8.py b/vllm/model_executor/layers/quantization/input_quant_fp8.py index 5bc78afa4..6fa85436d 100644 --- a/vllm/model_executor/layers/quantization/input_quant_fp8.py +++ b/vllm/model_executor/layers/quantization/input_quant_fp8.py @@ -85,7 +85,7 @@ class QuantFP8(CustomOp): x: torch.Tensor, scale: torch.Tensor | None = None, scale_ub: torch.Tensor | None = None, - **kwargs, + use_triton: bool = False, ) -> tuple[torch.Tensor, torch.Tensor]: from vllm.model_executor.layers.quantization.utils import fp8_utils @@ -135,9 +135,8 @@ class QuantFP8(CustomOp): x: torch.Tensor, scale: torch.Tensor | None = None, scale_ub: torch.Tensor | None = None, - **kwargs, + use_triton: bool = False, ) -> tuple[torch.Tensor, torch.Tensor]: - use_triton = kwargs.get("use_triton", False) if self.is_group_quant and use_triton: assert scale is None, "Dynamic group quantization does not use scale" @@ -171,6 +170,7 @@ class QuantFP8(CustomOp): x: torch.Tensor, scale: torch.Tensor | None = None, scale_ub: torch.Tensor | None = None, + use_triton: bool = False, ): if self.is_group_quant and not self.static: assert scale is None, "Dynamic group quantization does not use scale"