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

[Bugfix][CI] fix typos (#34934)

Browse Source 
Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Jiayi Yan
2026-03-06 01:05:46 +08:00
committed by GitHub
parent 8c760b6ab6
commit 6a895197fa
98 changed files with 227 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm/model_executor/models/phi4mm_audio.py
View File

@@ -689,19 +689,19 @@ class ConformerEncoder(TransformerEncoderBase):
default False.
ext_pw_out_channel: int, optional
the number of channel for CNN
before depthwise_seperable_CNN.
before depthwise_separable_CNN.
If 0 then use linear. default 0.
ext_pw_kernel_size: int, optional
kernel size of N before depthwise_seperable_CNN.
kernel size of N before depthwise_separable_CNN.
only work for ext_pw_out_channel > 0.
default 1
depthwise_seperable_out_channel: int, optional
the number of channel for
depthwise_seperable_CNN.
depthwise_separable_CNN.
default 256.
depthwise_multiplier: int, optional
the number of multiplier for
depthwise_seperable_CNN.
depthwise_separable_CNN.
default 1.
chunk_se: int, optional
0 for offline SE.
@@ -711,7 +711,7 @@ class ConformerEncoder(TransformerEncoderBase):
by only the current chunk.
default 0.
kernel_size: int, optional
the number of kernels for depthwise_seperable_CNN.
the number of kernels for depthwise_separable_CNN.
default 3.
activation: str, optional
FeedForward block activation.
@@ -721,7 +721,7 @@ class ConformerEncoder(TransformerEncoderBase):
activation function used in ConvModule part
of the conformer, default "relu".
conv_glu_type: str, optional
activation used use glu in depthwise_seperable_CNN,
activation used use glu in depthwise_separable_CNN,
default "sigmoid"
bias_in_glu: bool, optional
if set to True, use additive bias in the weight module