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
554df8a6
Unverified
Commit
554df8a6
authored
Aug 02, 2025
by
Xiao
Committed by
GitHub
Aug 02, 2025
Browse files
Revert "[compile][startup] Disable C++ compilation of symbolic shapes" (#22122)
Signed-off-by:
Xiao Liu
<
xiszishu@gmail.com
>
parent
73e1b9b1
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
9 deletions
+2
-9
vllm/compilation/decorators.py
vllm/compilation/decorators.py
+2
-9
No files found.
vllm/compilation/decorators.py
View file @
554df8a6
...
...
@@ -267,14 +267,7 @@ def _support_torch_compile(
code
.
co_filename
)
return
inline_call
(
parent
,
func
,
args
,
kwargs
)
# Disable the C++ compilation of symbolic shape guards. C++-fication
# of symbolic shape guards can improve guard overhead. But, since
# vllm skip guards anyways, setting this flag to False can improve
# compile time.
with
torch
.
_dynamo
.
config
.
patch
(
"enable_cpp_symbolic_shape_guards"
,
False
),
patch
.
object
(
InliningInstructionTranslator
,
'inline_call'
,
with
patch
.
object
(
InliningInstructionTranslator
,
'inline_call'
,
patched_inline_call
):
output
=
self
.
compiled_callable
(
*
args
,
**
kwargs
)
return
output
...
...
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