Skip to content

[BugFix] Fix KSM overlap bug #7772

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
Deleter-D wants to merge 1 commit into
base: release/2.6
Choose a base branch
from
+1 −3
Open

[BugFix] Fix KSM overlap bug #7772

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: 1 addition & 3 deletions fastdeploy/model_executor/pre_and_post_process.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -585,9 +585,7 @@ def save_output_speculate(

# Renormalize logprobs with logz (deferred from post_process for better overlap).
if sampler_output.logprobs_tensors is not None and sampler_output.logz_per_batch is not None:
# TODO (wangyanpeng): Currently, there is a bug when overlap is enabled.
# Please ensure overlap is disabled when using this functionality to avoid unexpected behavior.
real_token_num = share_inputs["accept_num_cpu"].sum()
real_token_num = share_inputs["accept_num"].sum()
sampler_output.logprobs_tensors = LogprobsTensors(
logprob_token_ids=sampler_output.logprobs_tensors.logprob_token_ids[:real_token_num],
logprobs=sampler_output.logprobs_tensors.logprobs[:real_token_num],
Expand Down
Loading