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
cbeaf0b5
"vscode:/vscode.git/clone" did not exist on "11cd1ae6ad6fa7d35060fea35133e08c0a1c227c"
Commit
cbeaf0b5
authored
Mar 17, 2025
by
zhuwenwen
Browse files
update fused_moe.py
parent
2b47d4fa
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
3 deletions
+1
-3
vllm/model_executor/layers/fused_moe/fused_moe.py
vllm/model_executor/layers/fused_moe/fused_moe.py
+1
-3
No files found.
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @
cbeaf0b5
...
...
@@ -918,9 +918,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
assert
B_scale
is
None
EM
=
sorted_token_ids
.
shape
[
0
]
if
use_int4_w4a16
:
EM
=
sorted_token_ids
.
shape
[
0
]
elif
A
.
shape
[
0
]
<
config
[
"BLOCK_SIZE_M"
]:
if
A
.
shape
[
0
]
<
config
[
"BLOCK_SIZE_M"
]:
# optimize for small batch_size.
# We assume that top_ids of each token is unique, so
# so num_valid_experts <= batch_size <= BLOCK_SIZE_M,
...
...
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