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
d1adb9b4
Unverified
Commit
d1adb9b4
authored
Jan 17, 2025
by
Chen Zhang
Committed by
GitHub
Jan 17, 2025
Browse files
[BugFix] add more `is not None` check in VllmConfig.__post_init__ (#12138)
Signed-off-by:
Chen Zhang
<
zhangch99@outlook.com
>
parent
b8bfa46a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
1 deletion
+2
-1
vllm/config.py
vllm/config.py
+2
-1
No files found.
vllm/config.py
View file @
d1adb9b4
...
@@ -3174,7 +3174,8 @@ class VllmConfig:
...
@@ -3174,7 +3174,8 @@ class VllmConfig:
if
self
.
compilation_config
is
None
:
if
self
.
compilation_config
is
None
:
self
.
compilation_config
=
CompilationConfig
()
self
.
compilation_config
=
CompilationConfig
()
if
envs
.
VLLM_USE_V1
and
not
self
.
model_config
.
enforce_eager
:
if
envs
.
VLLM_USE_V1
and
self
.
model_config
is
not
None
and
\
not
self
.
model_config
.
enforce_eager
:
# NOTE(woosuk): Currently, we use inductor because the piecewise
# NOTE(woosuk): Currently, we use inductor because the piecewise
# CUDA graphs do not work properly with the custom CUDA kernels.
# CUDA graphs do not work properly with the custom CUDA kernels.
# FIXME(woosuk): Disable inductor to reduce the compilation time
# FIXME(woosuk): Disable inductor to reduce the compilation time
...
...
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