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
00c4cb56
Unverified
Commit
00c4cb56
authored
Mar 09, 2026
by
Matthew Bonanni
Committed by
GitHub
Mar 09, 2026
Browse files
[Bugfix] Clear stale CG keys after memory profiling (#36416)
Signed-off-by:
Matthew Bonanni
<
mbonanni@redhat.com
>
parent
941e52c2
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
0 deletions
+3
-0
vllm/v1/worker/gpu_model_runner.py
vllm/v1/worker/gpu_model_runner.py
+3
-0
No files found.
vllm/v1/worker/gpu_model_runner.py
View file @
00c4cb56
...
...
@@ -5644,6 +5644,9 @@ class GPUModelRunner(
for
instance
in
list
(
CUDAGraphWrapper
.
_all_instances
):
if
id
(
instance
)
in
original_pools
:
instance
.
graph_pool
=
original_pools
[
id
(
instance
)]
for
key_set
in
self
.
cudagraph_dispatcher
.
cudagraph_keys
.
values
():
key_set
.
clear
()
self
.
cudagraph_dispatcher
.
keys_initialized
=
False
self
.
maybe_remove_all_loras
(
self
.
lora_config
)
self
.
_cleanup_profiling_kv_cache
()
compilation_counter
.
num_cudagraph_captured
=
saved_num_cudagraph_captured
...
...
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