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

[Misc]Reduce BNB static variable #9987

Merged
merged 2 commits into from
Nov 4, 2024

Conversation

jeejeelee
Copy link
Collaborator

@jeejeelee jeejeelee commented Nov 4, 2024

Obtain weight sharding information directly from the model rather than through extra static variable, simplifying the support process for BNB quantization.
With this PR, models that support BNB quantization (such as Qwen2) can now directly support TP.

ping @mgoin @chenqianfzh

Signed-off-by: Jee Jee Li <[email protected]>
Copy link

github-actions bot commented Nov 4, 2024

👋 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.

🚀

@DarkLight1337 DarkLight1337 requested a review from mgoin November 4, 2024 09:44
Copy link
Member

@mgoin mgoin left a comment

Choose a reason for hiding this comment

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

Much much nicer to do it this way, nice work.

vllm/model_executor/models/gemma.py Outdated Show resolved Hide resolved
@mgoin mgoin added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 4, 2024
Signed-off-by: Jee Jee Li <[email protected]>
@jeejeelee jeejeelee requested a review from mgoin November 4, 2024 15:37
@mgoin mgoin enabled auto-merge (squash) November 4, 2024 15:47
@mgoin mgoin merged commit fb2716d into vllm-project:main Nov 4, 2024
60 checks passed
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Nov 4, 2024
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Nov 4, 2024
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Linkun Chen <[email protected]>
richardsliu pushed a commit to richardsliu/vllm that referenced this pull request Nov 4, 2024
@jeejeelee jeejeelee deleted the reduce-bnb-static-var branch November 5, 2024 01:25
bigPYJ1151 pushed a commit to bigPYJ1151/vllm that referenced this pull request Nov 5, 2024
DarkLight1337 pushed a commit that referenced this pull request Nov 5, 2024
JC1DA pushed a commit to JC1DA/vllm that referenced this pull request Nov 11, 2024
sumitd2 pushed a commit to sumitd2/vllm that referenced this pull request Nov 14, 2024
KuntaiDu pushed a commit to KuntaiDu/vllm that referenced this pull request Nov 20, 2024
mfournioux pushed a commit to mfournioux/vllm that referenced this pull request Nov 20, 2024
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Maxime Fournioux <[email protected]>
tlrmchlsmth pushed a commit to neuralmagic/vllm that referenced this pull request Nov 23, 2024
Signed-off-by: Jee Jee Li <[email protected]>
Signed-off-by: Tyler Michael Smith <[email protected]>
sleepwalker2017 pushed a commit to sleepwalker2017/vllm that referenced this pull request Dec 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants