Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
OpenDAS
vllm_cscc
Commits
10184690
Commit
10184690
authored
Jun 23, 2025
by
zhuwenwen
Browse files
fix moe run error
parent
675d3e87
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
5 additions
and
5 deletions
+5
-5
vllm/model_executor/layers/fused_moe/fused_moe.py
vllm/model_executor/layers/fused_moe/fused_moe.py
+1
-1
vllm/model_executor/layers/fused_moe/moe_align_block_size.py
vllm/model_executor/layers/fused_moe/moe_align_block_size.py
+4
-4
No files found.
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @
10184690
...
@@ -5,7 +5,7 @@ import functools
...
@@ -5,7 +5,7 @@ import functools
import
json
import
json
import
os
import
os
import
math
import
math
from
typing
import
Any
,
Callable
,
Optional
,
List
,
Optional
,
Tuple
from
typing
import
Any
,
Callable
,
Dict
,
Optional
,
List
,
Optional
,
Tuple
import
torch
import
torch
...
...
vllm/model_executor/layers/fused_moe/moe_align_block_size.py
View file @
10184690
# SPDX-License-Identifier: Apache-2.0
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from
typing
import
Optional
from
typing
import
Optional
,
Tuple
import
torch
import
torch
...
@@ -153,9 +153,9 @@ def moe_align_block_size(
...
@@ -153,9 +153,9 @@ def moe_align_block_size(
block_size
:
int
,
block_size
:
int
,
num_experts
:
int
,
num_experts
:
int
,
expert_map
:
Optional
[
torch
.
Tensor
]
=
None
,
expert_map
:
Optional
[
torch
.
Tensor
]
=
None
,
pad_sorted_ids
:
bool
=
False
pad_sorted_ids
:
bool
=
False
,
num_token
:
Optional
[
int
]
=
None
num_token
:
Optional
[
int
]
=
None
)
->
t
uple
[
torch
.
Tensor
,
torch
.
Tensor
,
torch
.
Tensor
]:
)
->
T
uple
[
torch
.
Tensor
,
torch
.
Tensor
,
torch
.
Tensor
]:
"""
"""
Aligns the token distribution across experts to be compatible with block
Aligns the token distribution across experts to be compatible with block
size for matrix multiplication.
size for matrix multiplication.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment