From c154d89306bf9978ff013659c5b1244af78386cc Mon Sep 17 00:00:00 2001
From: GiantCroc <1204449533@qq.com>
Date: Wed, 21 May 2025 21:45:57 +0800
Subject: [PATCH] [Doc] fix arg docstring in linear layers (#18410)

Signed-off-by: giantcroc <1204449533@qq.com>
---
 vllm/model_executor/layers/linear.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/vllm/model_executor/layers/linear.py b/vllm/model_executor/layers/linear.py
index 54dd1251e59ff..dd2e477f3954b 100644
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
@@ -261,6 +261,7 @@ class ReplicatedLinear(LinearBase):
         quant_config: Quantization configure.
         prefix: The name of the layer in the state dict, including all parents
                         (e.g. model.layers.0.qkv_proj)
+        return_bias: If true, return bias together with outputs in forward pass.
     """
 
     def __init__(
@@ -523,6 +524,7 @@ class MergedColumnParallelLinear(ColumnParallelLinear):
         quant_config: Quantization configure.
         prefix: The name of the layer in the state dict, including all parents
                         (e.g. model.layers.0.qkv_proj)
+        return_bias: If true, return bias together with outputs in forward pass.
     """
 
     def __init__(
@@ -805,6 +807,7 @@ class QKVParallelLinear(ColumnParallelLinear):
         quant_config: Quantization configure.
         prefix: The name of the layer in the state dict, including all parents
                         (e.g. model.layers.0.qkv_proj)
+        return_bias: If true, return bias together with outputs in forward pass.
     """
 
     def __init__(
@@ -1155,7 +1158,13 @@ class RowParallelLinear(LinearBase):
                        bias can be fused with other element-wise operations.
                        We skip adding bias but instead return it.
         params_dtype: Data type for the parameters.
+        reduce_results: If true, call all-reduce on output and make Y available
+                       to all GPUs, otherwise, every GPU will have its output
+                       which is Y = X_iA_i
         quant_config: Quantization configure.
+        prefix: The name of the layer in the state dict, including all parents
+                        (e.g. model.layers.0.down_proj)
+        return_bias: If true, return bias together with outputs in forward pass.
     """
 
     def __init__(