Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Feature]: Restore support for 2-bit and 3-bit GPTQ [1 pull requests]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Fix Action

Fixed

RAW_BUFFERClick to expand / collapse

🚀 The feature, motivation and pitch

In the recent GPTQ consolidation PR (#38288), it appears that the AutoGPTQ class dropped support for 2-bit and 3-bit GPTQ configurations. (Reference: https://github.com/vllm-project/vllm/pull/38288#issuecomment-4617004876 by @cnie-rblx). Since Marlin does not support 2-bit and 3-bit, they are still valuable for extremely low-bit quantization.

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING