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
fbc0abba
Commit
fbc0abba
authored
Jul 21, 2025
by
zhuwenwen
Browse files
fix moe error
parent
029da5e8
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
vllm/model_executor/layers/fused_moe/fused_moe.py
vllm/model_executor/layers/fused_moe/fused_moe.py
+3
-3
No files found.
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @
fbc0abba
...
...
@@ -4,7 +4,7 @@
import
functools
import
json
import
os
from
typing
import
Any
,
Callable
,
Optional
,
List
,
Optional
,
Tuple
from
typing
import
Any
,
Callable
,
Optional
,
List
,
Optional
,
Tuple
,
Dict
import
torch
...
...
@@ -502,7 +502,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
use_int8_w8a16
:
bool
,
use_int4_w4a16
:
bool
,
per_channel_quant
:
bool
,
block_shape
:
Optional
[
List
[
int
]
,
]
=
None
,
block_shape
:
Optional
[
List
[
int
]]
=
None
,
use_nn_moe
:
Optional
[
bool
]
=
False
)
->
None
:
assert
topk_weights
is
not
None
or
not
mul_routed_weight
assert
topk_weights
is
None
or
topk_weights
.
stride
(
1
)
==
1
...
...
@@ -679,7 +679,7 @@ def get_moe_configs(
block_n
:
Optional
[
int
]
=
None
,
block_k
:
Optional
[
int
]
=
None
,
use_nn_moe
:
Optional
[
bool
]
=
False
,
)
->
Optional
[
d
ict
[
int
,
Any
]]:
)
->
Optional
[
D
ict
[
int
,
Any
]]:
"""
Return optimized configurations for the fused MoE kernel.
...
...
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