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
e18f0851
Unverified
Commit
e18f0851
authored
Jul 29, 2025
by
Calvin Chen
Committed by
GitHub
Jul 28, 2025
Browse files
skip fusedmoe layer for start_load_kv (#21378)
Signed-off-by:
calvin chen
<
wen.chen@dynamia.ai
>
parent
afa26075
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
10 additions
and
2 deletions
+10
-2
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py
...ted/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py
+10
-2
No files found.
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py
View file @
e18f0851
...
@@ -192,8 +192,16 @@ class P2pNcclConnector(KVConnectorBase_V1):
...
@@ -192,8 +192,16 @@ class P2pNcclConnector(KVConnectorBase_V1):
# Load the KV for each request each layer
# Load the KV for each request each layer
for
request
in
metadata
.
requests
:
for
request
in
metadata
.
requests
:
for
layer_name
in
forward_context
.
no_compile_layers
:
for
layer_name
in
forward_context
.
no_compile_layers
:
attn_layer
=
forward_context
.
no_compile_layers
[
layer_name
]
layer
=
forward_context
.
no_compile_layers
[
layer_name
]
kv_cache_layer
=
attn_layer
.
kv_cache
[
\
# Only process layers that have kv_cache
# attribute (attention layers) Skip non-attention
# layers like FusedMoE
kv_cache
=
getattr
(
layer
,
'kv_cache'
,
None
)
if
kv_cache
is
None
:
continue
kv_cache_layer
=
kv_cache
[
\
forward_context
.
virtual_engine
]
forward_context
.
virtual_engine
]
kv_cache
=
self
.
p2p_nccl_engine
.
recv_tensor
(
kv_cache
=
self
.
p2p_nccl_engine
.
recv_tensor
(
...
...
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