Skip to content

[BugFix] Fix shared storage connector load kv only load attention layer #21428

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 2 commits into from
Jul 26, 2025
+10 −2
Merged

[BugFix] Fix shared storage connector load kv only load attention layer #21428

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
62b4073
fix shared storage connector load kv only attention layer
david6666666 Jul 23, 2025
f1c6227
fix shared storage connector load kv only attention layer
david6666666 Jul 23, 2025
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/shared_storage_connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,8 +156,16 @@ def inject_kv_into_layer(
logger.info("Inject KV cache of %d tokens to the paged memory",
len(request.slot_mapping))
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/MLP etc.
kv_cache_attr = getattr(layer, 'kv_cache', None)
if kv_cache_attr is None:
continue

kv_cache_layer = kv_cache_attr[ \
forward_context.virtual_engine]

filename = self._generate_filename_debug(
Expand Down