Skip to content

[bugfix]adapt vllm >= 0.11.0 #429

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

Closed
qyh111 wants to merge 1 commit into from
Closed

[bugfix]adapt vllm >= 0.11.0 #429

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
5 changes: 4 additions & 1 deletion ucm/integration/vllm/ucm_connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ def __init__(self, vllm_config: "VllmConfig", role: KVConnectorRole):
if self.metrics_config:
self.stats_logger = UCMStatsLogger(
vllm_config.model_config.served_model_name,
self.rank,
self.global_rank,
self.metrics_config,
)
self.monitor = ucmmonitor.StatsMonitor.get_instance()
Expand Down Expand Up @@ -332,6 +332,9 @@ def build_connector_meta(
continue
req_meta = self.requests_meta.get(request_id)
if req_meta:
# when vllm >= 0.11.0 new_block_ids could be NONE
if scheduled_cached_reqs.new_block_ids[i] is None:
continue
requests_dispatch_meta[request_id] = self._generate_dispatch_meta(
req_meta,
scheduler_output.num_scheduled_tokens[request_id],
Expand Down