lm-sys / lm-sys/FastChat

gptq inference problem

Open
#1,918 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

image

I'm confused about this code. act_order is a bool parameter(True or False), in this code, only when act_order is True, it will be passed to the function load_quant. And the default value of act_order in branch fastest-inference-4bit is True. So the act_order is always True, is that right?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing the act_order parameter and the load_quant call in the fastest-inference-4bit branch, using the code shown in the issue. Confirm whether the default causes act_order to remain True and determine whether the observed behavior is incorrect; done means the parameter flow and expected setting are clear.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.