xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Doc] fix arg docstring in linear layers (#18410)

Browse Source 
Signed-off-by: giantcroc <1204449533@qq.com>
This commit is contained in:
GiantCroc 2025-05-21 21:45:57 +08:00 committed by GitHub
parent eca18691d2
commit c154d89306
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
vllm/model_executor/layers/linear.py
View File

@ -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__(