Skip to content

[BugFix] Fix Smoke Testing Bug for DSR1 longseq #5613

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
wangxiyuan merged 1 commit into from
Jan 5, 2026
Merged

[BugFix] Fix Smoke Testing Bug for DSR1 longseq #5613

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: 2 additions & 2 deletions tests/e2e/nightly/multi_node/config/DeepSeek-R1-W8A8-longseq.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ deployment:
--seed 1024
--quantization ascend
--max-num-seqs 4
--max-model-len 32768
--max-model-len 36864
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot Jan 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

The max-model-len value is duplicated in the second deployment configuration on line 75. To improve maintainability and prevent future inconsistencies where one value is updated but the other is not, consider defining this value as a variable in the env_common section and referencing it in both server_cmd blocks.

For example, you could add MAX_MODEL_LEN: 36864 to env_common and then use --max-model-len $MAX_MODEL_LEN in both deployment commands. This pattern is already used for $SERVER_PORT.

--max-num-batched-tokens 16384
--trust-remote-code
--gpu-memory-utilization 0.9
Expand Down Expand Up @@ -72,7 +72,7 @@ deployment:
--seed 1024
--quantization ascend
--max-num-seqs 4
--max-model-len 32768
--max-model-len 36864
--max-num-batched-tokens 256
--trust-remote-code
--gpu-memory-utilization 0.9
Expand Down
Loading