Skip to content

[Bug Fix][Cherry-pick] Fix bug for caching output when preempted #5510

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

Open
rainyfly wants to merge 1 commit into
base: release/2.4
Choose a base branch
from
Open

[Bug Fix][Cherry-pick] Fix bug for caching output when preempted #5510

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
4 changes: 3 additions & 1 deletion fastdeploy/output/token_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -750,7 +750,9 @@ def _process_batch_output(self):
and self.cfg.cache_config.enable_prefix_caching
and self.cfg.cache_config.enable_output_caching
):
if (task.num_total_tokens - 1) % self.cfg.cache_config.block_size == 0:
if (task.num_total_tokens - 1) % self.cfg.cache_config.block_size == 0 and (
task_id not in self.resource_manager.to_be_rescheduled_request_id_set
):
self.resource_manager.cache_output_tokens(
task
) # when enable prefix caching, cache kv cache for output tokens
Expand Down
Loading