Skip to content

reduce maxTokens for glm-4-9b-chat to fit 50GB GPU #47

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
nicole-lihui wants to merge 1 commit into
base: main
Choose a base branch
from
Open

reduce maxTokens for glm-4-9b-chat to fit 50GB GPU #47

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 models/zhipuai/glm-4-9b-chat/metadata.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,9 @@ spec:
config:
maxTokens: 128000
deployments:
- customRuntimeArgs: []
- customRuntimeArgs:
- --max-num-batched-tokens=32768 # Reduce maxTokens from 128k to 32k to fit 50GB GPU and avoid OOM
Copy link
Contributor

@kebe7jun kebe7jun Oct 23, 2025

Choose a reason for hiding this comment

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

一般不要设置到最大长度，单机的情况下可以不修改。

- --max-model-len=32768 # Align max-model-len with max-num-batched-tokens for stable inference
resourceRequirements:
cpu: 4
gpuCount: 1
Expand Down