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
97f92c6b
Unverified
Commit
97f92c6b
authored
Apr 03, 2026
by
Nicolò Lucchesi
Committed by
GitHub
Apr 03, 2026
Browse files
[KVConnector] Skip `register_kv_caches` on profiling (#38558)
Signed-off-by:
NickLucche
<
nlucches@redhat.com
>
parent
46f02e00
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
vllm/v1/worker/gpu_model_runner.py
vllm/v1/worker/gpu_model_runner.py
+1
-1
No files found.
vllm/v1/worker/gpu_model_runner.py
View file @
97f92c6b
...
@@ -6844,7 +6844,7 @@ class GPUModelRunner(
...
@@ -6844,7 +6844,7 @@ class GPUModelRunner(
# group
# group
self
.
drafter
.
validate_same_kv_cache_group
(
kv_cache_config
)
self
.
drafter
.
validate_same_kv_cache_group
(
kv_cache_config
)
if
has_kv_transfer_group
():
if
has_kv_transfer_group
()
and
not
is_profiling
:
kv_transfer_group
=
get_kv_transfer_group
()
kv_transfer_group
=
get_kv_transfer_group
()
if
self
.
cross_layers_kv_cache
is
not
None
:
if
self
.
cross_layers_kv_cache
is
not
None
:
assert
self
.
cross_layers_attn_backend
is
not
None
assert
self
.
cross_layers_attn_backend
is
not
None
...
...
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