Skip to content

[Refactor] Refactor FP8 & INT8 Quant Folder inside 8bit #22474

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

Open
wants to merge 5 commits into
base: main
Choose a base branch
from

Conversation

yewentao256
Copy link
Collaborator

@yewentao256 yewentao256 commented Aug 7, 2025

Purpose

Refactor FP8 & INT8 Quant Folder inside 8bit for better code maintainability

Test

lm_eval   --model vllm   --model_args "pretrained=Qwen/Qwen3-30B-A3B-FP8,max_model_len=32768,enforce_eager=True"   --trust_remote_code   --tasks gsm8k   --num_fewshot 5   --batch_size auto
vllm (pretrained=Qwen/Qwen3-30B-A3B-FP8,max_model_len=32768,enforce_eager=True,trust_remote_code=True), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.8279|±  |0.0104|
|     |       |strict-match    |     5|exact_match|↑  |0.8961|±  |0.0084|
# main
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.8264|±  |0.0104|
|     |       |strict-match    |     5|exact_match|↑  |0.8954|±  |0.0084|

Signed-off-by: yewentao256 <[email protected]>
Copy link

github-actions bot commented Aug 7, 2025

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

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 either: Add ready label to the PR or enable auto-merge.

🚀

@mergify mergify bot added the ci/build label Aug 7, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request refactors the FP8 and INT8 quantization code into a new 8bit directory, which improves code organization and maintainability. The changes primarily involve moving files, updating include paths, and cleaning up some comments. The logic appears to be preserved correctly. I have one suggestion regarding a removed comment that provided important context for preventing potential integer overflow issues.

Signed-off-by: yewentao256 <[email protected]>
@yewentao256 yewentao256 added the ready ONLY add when PR is ready to merge/full CI is needed label Aug 12, 2025
@yewentao256
Copy link
Collaborator Author

@mgoin CC

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ci/build 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.

1 participant