Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
2f6bacee
Unverified
Commit
2f6bacee
authored
Mar 13, 2025
by
Cheng Wan
Committed by
GitHub
Mar 12, 2025
Browse files
[moe] fix: correct the cache size in the last chunk (#3679)
Co-authored-by:
Abatom
<
abzhonghua@gmail.com
>
parent
40148041
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
1 deletion
+3
-1
python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
+3
-1
No files found.
python/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py
View file @
2f6bacee
...
...
@@ -1064,7 +1064,9 @@ def fused_experts_impl(
# so the cache size and config are already set correctly and
# do not need to be adjusted.
intermediate_cache1
=
intermediate_cache1
[:
tokens_in_chunk
]
intermediate_cache2
=
intermediate_cache2
[:
tokens_in_chunk
]
intermediate_cache2
=
intermediate_cache2
[
:
tokens_in_chunk
*
topk_ids
.
shape
[
1
]
]
intermediate_cache3
=
intermediate_cache3
[:
tokens_in_chunk
]
config
=
get_config_func
(
tokens_in_chunk
)
...
...
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