Skip to content

[V1][Minor] Remove obsolete FIXME comment #14304

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
Mar 5, 2025
+0 −5
Merged

[V1][Minor] Remove obsolete FIXME comment #14304

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: 0 additions & 5 deletions vllm/v1/worker/gpu_input_batch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,11 +298,6 @@ def add_request(
if sampling_params.logit_bias is not None:
self.logit_bias[req_index] = sampling_params.logit_bias

# FIXME: this implementation is incorrect. We create this mask
# then apply -inf to these specific tokens, which means we never
# select the allowed tokens! We cannot do the reverse, since
# this will impact the requests that do not have allowed_token_ids.
# This feature is currently disabled on V1 (we reject in Processor).
if sampling_params.allowed_token_ids:
self.has_allowed_token_ids.add(req_id)
if self.allowed_token_ids_mask_cpu_tensor is None:
Expand Down