Skip to content

skip fusedmoe layer for start_load_kv #21378

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 29, 2025
Merged

skip fusedmoe layer for start_load_kv #21378

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,8 +192,16 @@ def inject_kv_into_layer(
# Load the KV for each request each layer
for request in metadata.requests:
for layer_name in forward_context.no_compile_layers:
attn_layer = forward_context.no_compile_layers[layer_name]
kv_cache_layer = attn_layer.kv_cache[ \
layer = forward_context.no_compile_layers[layer_name]

# 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]

kv_cache = self.p2p_nccl_engine.recv_tensor(
Expand Down