Skip to content

[deepseek_r1] decrease default max_seq_len_to_capture from 8192->4096 to reduce prompt graph #1447

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
Jun 23, 2025
Merged

[deepseek_r1] decrease default max_seq_len_to_capture from 8192->4096 to reduce prompt graph #1447

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
2 changes: 1 addition & 1 deletion vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,7 @@ class EngineArgs:
tokenizer_revision: Optional[str] = None
quantization: Optional[str] = None
enforce_eager: Optional[bool] = None
max_seq_len_to_capture: int = 8192
max_seq_len_to_capture: int = 4096
disable_custom_all_reduce: bool = False
tokenizer_pool_size: int = 0
# Note: Specifying a tokenizer pool by passing a class
Expand Down
Loading