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.

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

[Model] support bitsandbytes quantization with minicpm3 model #10682

Merged
merged 1 commit into from
Nov 28, 2024
Merged

[Model] support bitsandbytes quantization with minicpm3 model #10682

merged 1 commit into from
Nov 28, 2024

Conversation

zixuanzhang226
Copy link
Contributor

No description provided.

@github-actions GitHub Actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

@zixuanzhang226 zixuanzhang226 force-pushed the support-bitsandbytes-quantization-with-minicpm3-model branch 2 times, most recently from f5eee26 to 7d73b1b Compare November 27, 2024 01:06
@DarkLight1337
Copy link
Member

Can you link to an example HF repo that uses this quantization?

@zixuanzhang226
[Model] support bitsandbytes quantization with minicpm3 model
fab405b 
Signed-off-by: Ubuntu <zixuanzhang@bytedance.com>
@zixuanzhang226 zixuanzhang226 force-pushed the support-bitsandbytes-quantization-with-minicpm3-model branch from 7d73b1b to fab405b Compare November 27, 2024 22:01
@zixuanzhang226
Copy link
Contributor Author

zixuanzhang226 commented Nov 27, 2024 •
edited
Loading

Can you link to an example HF repo that uses this quantization?
Hello @DarkLight1337 Please refer to https://huggingface.co/openbmb/MiniCPM3-4B

@DarkLight1337
Copy link
Member

Can you link to an example HF repo that uses this quantization?
Hello @DarkLight1337 Please refer to https://huggingface.co/openbmb/MiniCPM3-4B

Oh, I forgot that you can perform in-flight quantization with bitsandbytes. Never mind.

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 28, 2024
jeejeelee
jeejeelee approved these changes Nov 28, 2024
View reviewed changes
Copy link
Collaborator

@jeejeelee jeejeelee left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Thanks for your contribution, I can generate the reasonable result locally (TP=1/2)

@zixuanzhang226
Copy link
Contributor Author

Hello @jeejeelee, would you please merge the code? Thank you!

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) November 28, 2024 05:05
@youkaichao youkaichao disabled auto-merge November 28, 2024 07:57
@youkaichao youkaichao merged commit 70dc14f into vllm-project:main Nov 28, 2024
57 of 59 checks passed
afeldman-nm pushed a commit to neuralmagic/vllm that referenced this pull request Dec 2, 2024
@zixuanzhang226 @afeldman-nm
[Model] support bitsandbytes quantization with minicpm3 model (vllm-p…
b5864e2 
…roject#10682)

Signed-off-by: Ubuntu <zixuanzhang@bytedance.com>
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
@zixuanzhang226
[Model] support bitsandbytes quantization with minicpm3 model (vllm-p…
72b504d 
…roject#10682)

Signed-off-by: Ubuntu <zixuanzhang@bytedance.com>
BKitor pushed a commit to BKitor/vllm that referenced this pull request Dec 30, 2024
@zixuanzhang226 @BKitor
[Model] support bitsandbytes quantization with minicpm3 model (vllm-p…
90894a0 
…roject#10682)

Signed-off-by: Ubuntu <zixuanzhang@bytedance.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Isotr0py Isotr0py Isotr0py left review comments

@jeejeelee jeejeelee jeejeelee approved these changes

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@zixuanzhang226 @DarkLight1337 @jeejeelee @Isotr0py @youkaichao