From 76ddeff2931d1a5bc4192815c6ed778541e9f59e Mon Sep 17 00:00:00 2001 From: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Date: Tue, 15 Jul 2025 23:09:13 -0400 Subject: [PATCH] [Doc] Remove duplicate docstring (#21012) Signed-off-by: yewentao256 --- vllm/model_executor/layers/quantization/utils/fp8_utils.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/vllm/model_executor/layers/quantization/utils/fp8_utils.py b/vllm/model_executor/layers/quantization/utils/fp8_utils.py index c093a9bfc4a60..20e7b444856e3 100644 --- a/vllm/model_executor/layers/quantization/utils/fp8_utils.py +++ b/vllm/model_executor/layers/quantization/utils/fp8_utils.py @@ -378,8 +378,6 @@ def per_token_group_quant_fp8( is supported for now. column_major_scales: Outputs scales in column major. out_q: Optional output tensor. If not provided, function will create. - tuple[torch.Tensor, torch.Tensor]: The quantized tensor and the - scaling factor for quantization. Returns: tuple[torch.Tensor, torch.Tensor]: The quantized tensor and the scaling factor.