biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Docs] Fix warnings in mkdocs build (#23649)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Signed-off-by: Hyogeun Oh (오효근) <ohg3417@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-08-27 03:19:23 +09:00
committed by GitHub
parent 9b0187003e
commit 730d0ac8b9
14 changed files with 66 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/layers/linear.py
View File

@@ -233,10 +233,10 @@ class LinearBase(CustomOp):
Args:
input_size: input dimension of the linear layer.
output_size: output dimension of the linear layer.
bias: If true, add bias.
skip_bias_add: If true, skip adding bias but instead return it.
params_dtype: Data type for the parameters.
quant_config: Quantization configure.
prefix: Prefix for parameter names.
return_bias: If true, return bias together with outputs in forward pass.
"""
@@ -378,13 +378,14 @@ class MergedReplicatedLinear(ReplicatedLinear):
Args:
input_size: input dimension of the linear layer.
output_size: output dimension of the linear layer.
output_sizes: list of output dimensions of the linear layer.
bias: If true, add bias.
skip_bias_add: If true, skip adding bias but instead return it.
params_dtype: Data type for the parameters.
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__(