Skip to content

Error occurs when loading the gemma model in bitsandbytes format. #2557

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

Jump to bottom
Merged
merged 3 commits into from
Dec 26, 2024
Merged

Error occurs when loading the gemma model in bitsandbytes format. #2557

merged 3 commits into from
Dec 26, 2024

Conversation

upskyy
Copy link
Contributor

@upskyy upskyy commented Dec 23, 2024 •
edited
Loading

Motivation

#2556

Modifications

I refer to vllm to solve the key error that occurs when loading in bitsandbytes format.

An error occurs when loading the gemma model with the command below.

python3 -m sglang.launch_server --model-path /models --tokenizer-path /models --port 30000 --tokenizer-mode auto --dtype bfloat16 --mem-fraction-static 0.5 --random-seed 0 --enable-torch-compile --disable-cuda-graph --schedule-conservativeness 1.3 --kv-cache-dtype fp8_e5m2 --load-format bitsandbytes --quantization bitsandbytes

Checklist

  • Format your code according to the Contributor Guide.
  • Add unit tests as outlined in the Contributor Guide.
  • Update documentation as needed, including docstrings or example tutorials.

@merrymercy merrymercy merged commit 08effbf into sgl-project:main Dec 26, 2024
15 checks passed
@upskyy upskyy mentioned this pull request Dec 26, 2024
Closed
5 tasks
@merrymercy
Copy link
Contributor

@upskyy Thanks for the contribution. It is merged. Can you also help us fix this llama model? #2600

@upskyy upskyy mentioned this pull request Dec 27, 2024
Closed
@upskyy
Copy link
Contributor Author

upskyy commented Dec 27, 2024

@merrymercy
Looking at the code, I think the issue will also be resolved with the PR #2557. This problem occurred when changing to qweight when doing bitsandbytes 4bit load, but in the PR #2557, it was corrected not only for the gemma model but also for loads of other models.

timethink pushed a commit to timethink/sglang that referenced this pull request Mar 9, 2025
@upskyy
Error occurs when loading the gemma model in bitsandbytes format. (sg…
de8f342 
…l-project#2557)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@merrymercy merrymercy Awaiting requested review from merrymercy

@Ying1123 Ying1123 Awaiting requested review from Ying1123

@hnyls2002 hnyls2002 Awaiting requested review from hnyls2002

@zhyncs zhyncs Awaiting requested review from zhyncs

@ispobock ispobock Awaiting requested review from ispobock

@ByronHsu ByronHsu Awaiting requested review from ByronHsu

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@upskyy @merrymercy