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
5d16d0fa
Unverified
Commit
5d16d0fa
authored
Nov 05, 2025
by
Chen Zhang
Committed by
GitHub
Nov 05, 2025
Browse files
[DCP] check return_lse for all layers in dcp (#27929)
Signed-off-by:
Chen Zhang
<
zhangch99@outlook.com
>
parent
0606bea2
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
4 deletions
+1
-4
vllm/v1/worker/gpu_model_runner.py
vllm/v1/worker/gpu_model_runner.py
+1
-4
No files found.
vllm/v1/worker/gpu_model_runner.py
View file @
5d16d0fa
...
...
@@ -4680,10 +4680,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
kv_transfer_group
.
set_host_xfer_buffer_ops
(
copy_kv_blocks
)
if
self
.
dcp_world_size
>
1
:
layer_names
=
self
.
attn_groups
[
0
][
0
].
layer_names
layers
=
get_layers_from_vllm_config
(
self
.
vllm_config
,
AttentionLayerBase
,
layer_names
)
layers
=
get_layers_from_vllm_config
(
self
.
vllm_config
,
AttentionLayerBase
)
for
layer
in
layers
.
values
():
assert
layer
.
impl
.
need_to_return_lse_for_decode
,
(
"DCP requires attention impls to return"
...
...
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