Skip to content
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.

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

Mistral v0.3 Weight Loading #519

Closed
huyiwen opened this issue Jun 9, 2024 · 2 comments
Closed

Mistral v0.3 Weight Loading #519

huyiwen opened this issue Jun 9, 2024 · 2 comments
Assignees

Comments

@huyiwen
Copy link
Contributor

huyiwen commented Jun 9, 2024

Failed to launch the sglang server:

Run command: python -m sglang.launch_server --model-path Mistral-7B-Instruct-v0.3 --port 30000

Error message: KeyError: 'layers.0.attention.wk.weight'

This issue is also reported and fixed in vLLM.

@zhyncs zhyncs self-assigned this Jul 28, 2024
@zhyncs
Copy link
Member

zhyncs commented Jul 29, 2024

Hi @huyiwen May you try the latest version? I couldn't reproduce your issue on A100.

git clone https://github.com/sgl-project/sglang.git
cd sglang

pip install --upgrade pip
pip install -e "python[all]"

pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/

python3 -m sglang.launch_server --model mistralai/Mistral-7B-Instruct-v0.3

@zhyncs
Copy link
Member

zhyncs commented Jul 30, 2024

This issue has been closed because it cannot be reproduced in the latest version. Please feel free to reopen it if needed. Thanks.

@zhyncs zhyncs closed this as completed Jul 30, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants